© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    mentions of trails, paths, parks, and related outdoor recreational areas along with directional words.

    oai_token-act-pair · gemini-2.0-flash

    Paths and trails

    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
    ~
    -0.48
    нинград
    -0.42
    ou
    -0.41
    in
    -0.41
    <bos>
    -0.39
    9
    -0.39
    un
    -0.39
    wi
    -0.38
     at
    -0.38
     personali
    -0.37
    POSITIVE LOGITS
     виправивши
    1.13
    expandindo
    0.96
    XmlAccessType
    0.89
    RectangleBorder
    0.89
     utafitiHapana
    0.88
    principalTable
    0.87
    CloseOperation
    0.87
     resourceCulture
    0.86
    aarrggbb
    0.86
    verwijspagina
    0.86
    Activations Density 7.961%

    No Known Activations