© 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. 15214
    Prev
    Next
    INDEX
    Explanations

    code that uses imports and elle

    oai_token-act-pair · gemini-2.0-flash

    elle

    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
     Cha
    -0.43
    円
    -0.43
    redux
    -0.40
     dig
    -0.39
    chkin
    -0.38
     wohl
    -0.38
    ಧ
    -0.38
     As
    -0.38
    ását
    -0.37
     useCallback
    -0.37
    POSITIVE LOGITS
     beginnetje
    1.19
    contentLoaded
    1.11
     صوتيه
    1.06
    DockStyle
    1.04
     متعلقه
    1.02
     disambiguazione
    0.97
    تقاوى
    0.92
     الاطلاع
    0.87
    دانشنامهٔ
    0.84
     виправивши
    0.81
    Activations Density 0.550%

    No Known Activations