© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88514
    Prev
    Next
    INDEX
    Explanations

    portal, transport, item, level, model, code, controlled

    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
    0.75
    .
    0.75
    s
    0.69
    orb
    0.68
    an
    0.64
    ile
    0.63
    ani
    0.61
    och
    0.61
    et
    0.60
    Variable
    0.59
    POSITIVE LOGITS
    𝘁
    0.64
    з
    0.63
     esigen
    0.63
     Ве
    0.62
    کار
    0.61
     செயற்ப
    0.61
    в
    0.61
     केन्द्र
    0.60
    ı
    0.60
    կ
    0.59
    Activations Density 0.030%

    No Known Activations