© 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. 89149
    Prev
    Next
    INDEX
    Explanations

    lullaby

    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
    ने
    0.64
    ='.
    0.64
    ীয়
    0.62
    ग्विजय
    0.62
     stints
    0.60
     continuando
    0.58
     suffisante
    0.58
    тись
    0.58
     راجسټریشن
    0.57
    trees
    0.57
    POSITIVE LOGITS
    at
    0.93
    A
    0.84
    _
    0.83
    i
    0.79
    an
    0.77
     an
    0.77
    as
    0.76
    e
    0.71
    T
    0.71
     er
    0.70
    Activations Density 0.000%

    No Known Activations