© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87890
    Prev
    Next
    INDEX
    Explanations

    М

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     প্র
    0.52
     ר
    0.50
     דר
    0.50
    wa
    0.49
     רו
    0.49
    𝘻
    0.48
     світ
    0.48
    riy
    0.47
     грошы
    0.47
     і
    0.47
    POSITIVE LOGITS
    on
    0.67
     lads
    0.59
     lad
    0.58
    Lad
    0.58
    лад
    0.56
    Е
    0.55
     Lad
    0.54
    ла
    0.52
     ladle
    0.52
    емого
    0.50
    Activations Density 0.000%

    No Known Activations