© 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. 6306
    Prev
    Next
    INDEX
    Explanations

    language that is negative and shows some form of disappointment

    oai_token-act-pair · gemini-2.0-flash

    blog post snippets

    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
    UrlResolution
    -0.60
    PreExecute
    -0.56
    APORE
    -0.53
     """
    -0.50
    ódź
    -0.50
    ushchev
    -0.49
    THEW
    -0.49
    ,:),
    -0.48
    DataAnnotations
    -0.48
    ROLS
    -0.48
    POSITIVE LOGITS
    €¦
    0.61
     (...
    0.60
    migrationBuilder
    0.59
    .…
    0.54
     CreateTagHelper
    0.54
    ...
    0.54
    ...(
    0.54
    gameserver
    0.52
    interopRequire
    0.50
     intptr
    0.50
    Activations Density 17.432%

    No Known Activations