© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201133
    Prev
    Next
    INDEX
    Explanations

    learn and apply

    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_37_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
    oll
    0.45
    აწ
    0.40
     Pillar
    0.39
    iox
    0.38
     pillars
    0.38
    pillars
    0.38
    迩
    0.37
    تاء
    0.37
    дово
    0.37
    Bear
    0.36
    POSITIVE LOGITS
     Charcoal
    0.45
    肤
    0.43
     using
    0.42
     charcoal
    0.42
     ability
    0.41
     kasutada
    0.40
    alya
    0.39
     needs
    0.39
     unable
    0.39
     assets
    0.38
    Activations Density 0.002%

    No Known Activations