© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125869
    Prev
    Next
    INDEX
    Explanations

    Group Policy, music playlist, viruses, games

    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_3_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
    ’
    0.69
     centr
    0.58
    را
    0.55
     Chairperson
    0.54
    ు
    0.54
     ISR
    0.53
     prowess
    0.53
     quotient
    0.52
     r
    0.52
    wehr
    0.52
    POSITIVE LOGITS
    ુ
    0.89
    ל
    0.86
    ur
    0.75
    中の
    0.72
     activité
    0.71
    ри
    0.71
    ciri
    0.68
    ру
    0.68
    kę
    0.66
     développe
    0.66
    Activations Density 0.000%

    No Known Activations