© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51198
    Prev
    Next
    INDEX
    Explanations

    } parenthesis block

    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
     între
    0.38
    AssetsResponse
    0.36
    วน
    0.36
    如果没有
    0.36
    웅
    0.36
     если
    0.35
    㺫
    0.35
     можно
    0.34
    ylation
    0.34
    rends
    0.34
    POSITIVE LOGITS
     bula
    0.38
    ဈ
    0.37
     bully
    0.37
     Bulg
    0.37
     kuda
    0.35
     pledged
    0.35
    ROOT
    0.34
    लाइट
    0.34
     bul
    0.34
     horseback
    0.34
    Activations Density 0.006%

    No Known Activations