© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30878
    Prev
    Next
    INDEX
    Explanations

    ser + adjective/participle

    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_7_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
    2
    0.92
    for
    0.88
    el
    0.87
    itet
    0.86
    al
    0.85
    ،
    0.85
    ”،
    0.83
    iz
    0.82
    ov
    0.81
    ib
    0.79
    POSITIVE LOGITS
    0.81
    人
    0.75
     procédés
    0.66
    t
    0.66
     lumière
    0.60
     fallacy
    0.60
     завода
    0.60
     defiance
    0.59
     spazi
    0.59
     modelli
    0.58
    Activations Density 0.002%

    No Known Activations