© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136619
    Prev
    Next
    INDEX
    Explanations

    relationship or relative position

    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_12_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
    h
    0.35
     ".
    0.32
     evidente
    0.32
     sauvegard
    0.31
     некоторы
    0.31
     applauded
    0.31
     detecting
    0.30
     soliciting
    0.30
     traslado
    0.30
     dialogo
    0.30
    POSITIVE LOGITS
     Relationship
    0.39
    Relationship
    0.37
    Coin
    0.36
    ಟ
    0.33
    Puzzle
    0.33
     relationship
    0.32
    成品
    0.32
    мо
    0.31
    Relationships
    0.31
    Prediction
    0.30
    Activations Density 0.009%

    No Known Activations