© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14207
    Prev
    Next
    INDEX
    Explanations

    form attribute names

    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_34_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
    内外
    0.41
     cilia
    0.40
    fragen
    0.39
    ʺ
    0.38
    zellen
    0.38
    側面
    0.38
    ણો
    0.36
    osław
    0.36
    opholes
    0.36
    ⅝
    0.36
    POSITIVE LOGITS
    Form
    0.40
     груп
    0.38
     Group
    0.38
     Differential
    0.38
     Form
    0.38
     Cruise
    0.38
     value
    0.38
     گروه
    0.37
     Filing
    0.37
     autonomous
    0.36
    Activations Density 0.039%

    No Known Activations