© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10907
    Prev
    Next
    INDEX
    Explanations

    words used to describe people, potentially positive character traits

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    basicConfig
    -0.59
    }{*}{}
    -0.58
    modb
    -0.54
    springframework
    -0.52
    EndContext
    -0.50
    :✨
    -0.48
    "?>
    -0.46
    prits
    -0.45
     dry
    -0.45
     Straight
    -0.45
    POSITIVE LOGITS
    FormTagHelper
    0.67
    esModule
    0.59
    assies
    0.58
    principalColumn
    0.58
     كومونز
    0.57
    EDEFAULT
    0.55
    jerc
    0.53
     Italijani
    0.52
    vician
    0.51
    nodoc
    0.49
    Activations Density 5.060%

    No Known Activations