© 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. 12443
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly Go code, including keywords like "func," "return," "error," "Admin," and related symbols and structures.

    oai_token-act-pair · gemini-2.0-flash

    Code, errors, web development

    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
     propOrder
    -0.70
    Personendaten
    -0.58
     Galile
    -0.56
    iibo
    -0.52
    writeFieldEnd
    -0.52
     morire
    -0.51
    ValueStyle
    -0.51
    verifyException
    -0.51
    astify
    -0.50
    setArguments
    -0.49
    POSITIVE LOGITS
    ########.
    0.60
    hower
    0.53
    atier
    0.52
    orig
    0.52
     be
    0.51
    vuo
    0.50
    óbal
    0.50
    versch
    0.50
    bootstrapcdn
    0.50
    UniformLocation
    0.50
    Activations Density 3.898%

    No Known Activations