© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12212
    Prev
    Next
    INDEX
    Explanations

    out of

    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
    _
    0.62
     assurances
    0.55
     endorsement
    0.52
     sessions
    0.52
    j
    0.52
    $
    0.51
    /
    0.50
    e
    0.50
     Expression
    0.50
    ิร์
    0.50
    POSITIVE LOGITS
    është
    0.61
    ールド
    0.52
    luğu
    0.52
    টারি
    0.51
    luft
    0.49
    বন
    0.49
    ’)
    0.49
    вед
    0.49
     njia
    0.49
    䒠
    0.49
    Activations Density 0.026%

    No Known Activations