© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243239
    Prev
    Next
    INDEX
    Explanations

    actions and objects

    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_40_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
     CFM
    0.36
     accuracies
    0.36
    केजी
    0.35
    ధం
    0.35
     hük
    0.35
    avate
    0.35
    徫
    0.35
     LG
    0.34
     upped
    0.34
    邬
    0.34
    POSITIVE LOGITS
     line
    0.76
    line
    0.66
     lines
    0.66
     लाइन
    0.66
     линии
    0.65
    线
    0.65
     linea
    0.63
     линия
    0.63
    lines
    0.62
     خط
    0.61
    Activations Density 0.037%

    No Known Activations