© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199137
    Prev
    Next
    INDEX
    Explanations

    self-replicating

    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_15_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
     posticis
    0.61
    <unused226>
    0.56
     kttt
    0.55
     jungen
    0.54
     قيمه
    0.54
    𒃶
    0.54
     ناخذ
    0.54
    agangan
    0.53
     máme
    0.53
    <unused304>
    0.53
    POSITIVE LOGITS
    '
    0.50
     Disorders
    0.45
    >
    0.45
    ियो
    0.44
     Problems
    0.43
     Orphans
    0.42
    D
    0.42
     disorders
    0.41
     Thyroid
    0.41
    想
    0.41
    Activations Density 0.001%

    No Known Activations