© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227505
    Prev
    Next
    INDEX
    Explanations

    never forgot, came, lost

    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_6_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
    s
    1.23
    ی
    1.17
    u
    1.16
     is
    0.96
    i
    0.95
    ne
    0.91
    И
    0.89
    is
    0.84
    Σ
    0.82
    na
    0.79
    POSITIVE LOGITS
     اﻻ
    0.91
     мәкалә
    0.82
     Þ
    0.82
    гам
    0.81
    ák
    0.80
     كرد
    0.79
     avaliação
    0.79
     questões
    0.78
     সাংস্কৃতিক
    0.76
     ölç
    0.76
    Activations Density 0.001%

    No Known Activations