© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12694
    Prev
    Next
    INDEX
    Explanations

    people in jail asking to use a phone for legal reasons

    oai_token-act-pair · gemini-2.0-flash

    receive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    帖最后由
    -0.93
    oa̍t
    -0.70
     protoimpl
    -0.70
    RegistryLite
    -0.68
    tanleria
    -0.67
    complexContent
    -0.63
    TagMode
    -0.63
     незавершена
    -0.63
     Dernière
    -0.62
    toMatchSnapshot
    -0.62
    POSITIVE LOGITS
     received
    0.70
     receive
    0.69
    receive
    0.68
     receiving
    0.66
     RECEIVED
    0.64
    Receiving
    0.64
     receives
    0.62
    receiving
    0.62
     Receiving
    0.61
    received
    0.60
    Activations Density 2.431%

    No Known Activations