© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9725
    Prev
    Next
    INDEX
    Explanations

    pocket, pocketed, wifi, creators, monsters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ポー
    0.55
    레
    0.52
     озе
    0.50
    ').':
    0.50
    ポ
    0.49
     ఆదేశ
    0.49
    фа
    0.48
     انہیں
    0.48
     консо
    0.48
     때는
    0.47
    POSITIVE LOGITS
    Creators
    0.56
    commitment
    0.50
     creators
    0.49
     (
    0.49
     creator
    0.48
     momentum
    0.43
    creator
    0.43
     moderator
    0.43
    curve
    0.43
    al
    0.42
    Activations Density 0.000%

    No Known Activations