© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3255
    Prev
    Next
    INDEX
    Explanations

    unconnected punctuation, and pronouns such as "she", in stories and web pages.

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Efq
    -0.61
    ​—
    -0.59
    ]]
    -0.57
    "])
    -0.55
    […]
    -0.54
    ...";
    -0.54
    ScopeManager
    -0.53
    "]];
    -0.53
    ]};
    -0.52
     !...
    -0.51
    POSITIVE LOGITS
     المعيارى
    0.73
     مرئيه
    0.70
     finally
    0.65
    PerformLayout
    0.60
    komna
    0.60
    GOTREF
    0.58
    UpdateCommand
    0.57
    Aholisi
    0.56
    InsertCommand
    0.56
    stackSize
    0.56
    Activations Density 3.299%

    No Known Activations