© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252689
    Prev
    Next
    INDEX
    Explanations

    Greetings

    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_56_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
    UATION
    0.37
    メイ
    0.34
    舺
    0.33
     crud
    0.32
    チュア
    0.32
    رمپ
    0.31
    康
    0.31
     Controversy
    0.31
    頨
    0.31
     COW
    0.31
    POSITIVE LOGITS
     Greeting
    0.40
     புரிய
    0.40
     ley
    0.38
    Greeting
    0.38
    лями
    0.37
    oken
    0.35
     greeting
    0.35
    ieux
    0.35
    greeting
    0.35
    lessis
    0.34
    Activations Density 0.000%

    No Known Activations