© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8461
    Prev
    Next
    INDEX
    Explanations

    words related to the human body and its parts

    oai_token-act-pair · gemini-2.0-flash

    body parts and gaze

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    CodeAttribute
    -0.57
     jadx
    -0.54
    nofollow
    -0.54
    /***/
    -0.53
    belajaran
    -0.53
     Libri
    -0.51
    bulo
    -0.51
    Nobel
    -0.50
     Stadtteil
    -0.49
    pierw
    -0.49
    POSITIVE LOGITS
    fromnode
    0.74
    tonode
    0.59
     contextLoads
    0.55
    Obrázky
    0.54
    AutoScaleMode
    0.47
    ]),
    0.46
     tartalomajánló
    0.46
    Cre
    0.44
     eten
    0.44
    Right
    0.43
    Activations Density 3.897%

    No Known Activations