© 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. 5456
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically Python code using the "sys" module and file paths

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
    __':
    -0.50
    errHandler
    -0.46
     lagar
    -0.45
     a
    -0.45
     No
    -0.44
    RenderAtEndOf
    -0.44
    ma
    -0.43
     ma
    -0.42
    __':
    -0.41
    ModelSerializer
    -0.41
    POSITIVE LOGITS
     Efq
    0.87
     itſelf
    0.86
     iſt
    0.86
     Theſe
    0.85
     ſche
    0.84
     raiſ
    0.84
     myſelf
    0.80
     greateſt
    0.75
     AssemblyTitle
    0.75
    #+#
    0.75
    Activations Density 0.202%

    No Known Activations