© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225251
    Prev
    Next
    INDEX
    Explanations

    categorized by complexity

    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_10_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
    បំ
    0.41
    珑
    0.38
    كُمْ
    0.37
    роў
    0.36
    <unused2141>
    0.36
    ťou
    0.35
    ஜ்மஹ
    0.35
    𒄭
    0.35
    㗁
    0.35
    ون
    0.35
    POSITIVE LOGITS
    p
    0.44
    iv
    0.35
    is
    0.34
    isis
    0.33
     बल्ले
    0.32
    j
    0.32
    ya
    0.31
    -
    0.31
    Men
    0.31
    var
    0.30
    Activations Density 0.003%

    No Known Activations