© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12631
    Prev
    Next
    INDEX
    Explanations

    instances of actions or processes that are performed by one element without assistance

    oai_token-act-pair · gemini-2.0-flash

    alone

    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
     صوتيه
    -0.80
    ьаж
    -0.78
     TextFormField
    -0.74
     doubtnut
    -0.74
     itſelf
    -0.69
     GenerationType
    -0.69
     Formosa
    -0.69
     photolibrary
    -0.68
    Geplaatst
    -0.68
     XNUMX
    -0.68
    POSITIVE LOGITS
     est
    0.47
    idados
    0.43
    CppMethod
    0.43
     const
    0.42
     connecting
    0.42
    stateMutability
    0.42
     entre
    0.41
    cestry
    0.41
     im
    0.41
    </i>
    0.41
    Activations Density 12.639%

    No Known Activations