© 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. 4037
    Prev
    Next
    INDEX
    Explanations

    words relating to comic books or publishers

    oai_token-act-pair · gemini-2.0-flash

    Publications and comics

    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
    GetAxis
    -0.65
    fjspx
    -0.64
     contado
    -0.59
    帖最后由
    -0.58
    esModule
    -0.56
    SourceChecksum
    -0.50
    arwal
    -0.49
     cref
    -0.49
    
    -0.48
     handleMessage
    -0.48
    POSITIVE LOGITS
    ❮
    0.50
    المراجع
    0.48
    مراجع
    0.48
    breit
    0.45
     Dise
    0.45
    ագրություններ
    0.45
     calendriers
    0.45
    bine
    0.44
     înce
    0.43
    URSS
    0.43
    Activations Density 1.039%

    No Known Activations