© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 18-GEMMASCOPE-TRANSCODER-16K
    4. 7617
    Prev
    Next
    INDEX
    Explanations

    surrealist writing with political themes.

    oai_token-act-pair · gemini-2.0-flash

    asThe reason I'm choosing MAX_ACTIVATING_TOKENS explanation is that the question expects me to return an explanation if the above methods fail

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.39
     rhestr
    -0.38
     won
    -0.37
    awtextra
    -0.37
     GenerationType
    -0.36
    XtraBars
    -0.36
    >(_
    -0.36
     scrubbed
    -0.35
     invokingState
    -0.35
    脚注の使い方
    -0.35
    POSITIVE LOGITS
     onCancelled
    0.75
    fortawesome
    0.71
    RTEE
    0.69
    pherals
    0.64
     насељу
    0.63
    oredCriteria
    0.63
    发表于
    0.63
    хьтан
    0.62
    RegressionTest
    0.61
     disambiguazione
    0.60
    Activations Density 0.255%

    No Known Activations