© 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. 10595
    Prev
    Next
    INDEX
    Explanations

    the word "roll" or "rolling" near words related to mechanics or politics

    oai_token-act-pair · gemini-2.0-flash

    rolling

    np_max-act-logits · 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
     roll
    -2.86
     Roll
    -2.72
     rolled
    -2.66
     rolls
    -2.61
    Roll
    -2.59
     rolling
    -2.58
     ROLL
    -2.55
    roll
    -2.52
    rolling
    -2.36
     Rolling
    -2.36
    POSITIVE LOGITS
    httphttps
    0.53
    signOut
    0.52
     Honig
    0.48
     naturelles
    0.46
     Hick
    0.44
    addGap
    0.44
     fuite
    0.44
    )++;
    0.43
    itir
    0.43
     SwitchCompat
    0.43
    Activations Density 1.350%

    No Known Activations