© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141916
    Prev
    Next
    INDEX
    Explanations

    slipped through, away, in, inside, past

    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_12_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
    en
    0.67
    في
    0.58
    سي
    0.56
    es
    0.55
    V
    0.54
    ه
    0.54
     نظام
    0.54
    ❽
    0.53
     council
    0.52
    :
    0.52
    POSITIVE LOGITS
     lateribus
    0.60
     sentimiento
    0.59
     pensamientos
    0.59
    进士
    0.54
     visant
    0.54
    endid
    0.53
     thrombo
    0.53
     जैसा
    0.51
    ιά
    0.51
     साधारण
    0.51
    Activations Density 0.001%

    No Known Activations