© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58244
    Prev
    Next
    INDEX
    Explanations

    pyspark with import)

    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_2_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
    ad
    1.59
    _
    1.57
    am
    1.55
     be
    1.39
     can
    1.39
    ா
    1.38
    ed
    1.34
    ar
    1.33
    il
    1.33
    in
    1.30
    POSITIVE LOGITS
    дзе
    0.98
    <unused1049>
    0.93
     at
    0.91
    dale
    0.91
     Shrine
    0.91
    稹
    0.90
    }$,
    0.88
    dj
    0.87
    必要な
    0.86
    乸
    0.86
    Activations Density 0.001%

    No Known Activations