© 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. 4523
    Prev
    Next
    INDEX
    Explanations

    code-like text or potentially creative commons-like descriptions combined with art descriptions

    oai_token-act-pair · 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
     ProtoMessage
    -0.68
    asticity
    -0.66
    migrationBuilder
    -0.65
    ChildScrollView
    -0.65
    parsedMessage
    -0.64
    twimg
    -0.60
     pédagog
    -0.60
     refroidissement
    -0.60
     Theſe
    -0.59
     Efq
    -0.58
    POSITIVE LOGITS
     الاطلاع
    0.55
     Ved
    0.51
     يتيمه
    0.50
    rentiel
    0.50
    Spoljašnje
    0.49
     Me
    0.48
    msgSender
    0.48
    ParallelGroup
    0.48
     hat
    0.47
    بوابة
    0.46
    Activations Density 1.385%

    No Known Activations