© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193510
    Prev
    Next
    INDEX
    Explanations

    end of phrases

    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_4_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
     for
    0.90
    ER
    0.76
     déjà
    0.69
    ET
    0.67
     path
    0.67
    ’
    0.62
     kræ
    0.61
     die
    0.60
    '
    0.59
     case
    0.59
    POSITIVE LOGITS
    ール
    1.13
    ли
    1.11
    ية
    1.11
    на
    1.08
    л
    0.98
    ти
    0.91
    ב
    0.88
    з
    0.88
    то
    0.86
    ke
    0.85
    Activations Density 0.000%

    No Known Activations