© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11393
    Prev
    Next
    INDEX
    Explanations

    verbs, especially those implying progress through time or reaching a conclusion.

    oai_token-act-pair · gemini-2.0-flash

    Decisions or the name Liz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     пъ
    -0.47
    WithValue
    -0.45
     lembrar
    -0.45
     banheiro
    -0.45
    ticolo
    -0.44
    นวน
    -0.43
    responseText
    -0.42
     ikiwa
    -0.42
     assistir
    -0.42
     rainy
    -0.42
    POSITIVE LOGITS
    oredCriteria
    0.82
    rungsseite
    0.75
     GetEnumerator
    0.71
    ]--;
    0.70
    ]='\
    0.69
    InitVars
    0.67
     nahilalakip
    0.66
    mybatisplus
    0.65
    InsertCommand
    0.64
     Signalez
    0.63
    Activations Density 2.580%

    No Known Activations