© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37380
    Prev
    Next
    INDEX
    Explanations

    crucially

    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_11_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
    લમાં
    0.56
    COLORS
    0.55
    Ж
    0.54
    Throw
    0.52
    Charm
    0.52
    Albums
    0.51
    Surgery
    0.51
    i
    0.51
    ي
    0.51
    Repeating
    0.50
    POSITIVE LOGITS
     quantifiable
    0.63
     questionnaire
    0.60
     putea
    0.59
    х
    0.59
     ausreichend
    0.57
     bailar
    0.57
     aí
    0.56
     geopolitical
    0.56
     discount
    0.56
     reasonably
    0.56
    Activations Density 0.004%

    No Known Activations