© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53749
    Prev
    Next
    INDEX
    Explanations

    also, additionally

    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_30_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
    突出
    0.30
    呮
    0.29
    写入
    0.28
    arine
    0.28
     caractéristique
    0.27
    란
    0.27
    乑
    0.27
     എം
    0.26
    㳖
    0.26
    %/
    0.25
    POSITIVE LOGITS
     myös
    0.36
    also
    0.36
     أيضا
    0.34
     also
    0.32
     også
    0.32
    пру
    0.31
     Also
    0.30
     También
    0.30
     ايضا
    0.29
    management
    0.29
    Activations Density 0.099%

    No Known Activations