© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12162
    Prev
    Next
    INDEX
    Explanations

    code snippets, with particular focus on CURL and HTTP requests

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or code snippets

    np_token-act-pair-logits · gpt-4o-mini

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    findpost
    -0.88
     nakalista
    -0.81
    mtrl
    -0.69
    LookAnd
    -0.65
     Drapeau
    -0.65
     ModelExpression
    -0.62
     snippetHide
    -0.60
    最快更新
    -0.60
    MigrationBuilder
    -0.60
    ByPrimaryKey
    -0.59
    POSITIVE LOGITS
     grazia
    0.49
     userSchema
    0.47
    scaleY
    0.47
    })}\
    0.45
    yarnpkg
    0.44
    著
    0.44
    ClientSize
    0.44
     http
    0.43
    kaj
    0.42
     Blue
    0.41
    Activations Density 0.758%

    No Known Activations