© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164355
    Prev
    Next
    INDEX
    Explanations

    alphabetical sequences

    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_31_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
     stubborn
    0.38
     inferior
    0.38
    ளி
    0.37
    RICAL
    0.35
     الحلو
    0.35
    agia
    0.35
     [+
    0.34
     champ
    0.34
     Includes
    0.33
    𝘪
    0.33
    POSITIVE LOGITS
     letters
    0.41
     evidentemente
    0.41
    お問い合わせ
    0.40
    Letters
    0.40
     dollars
    0.38
     locations
    0.38
    ភា
    0.37
    dollars
    0.37
    显然
    0.37
     रवी
    0.36
    Activations Density 0.006%

    No Known Activations