© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138413
    Prev
    Next
    INDEX
    Explanations

    state management

    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
    topia
    0.53
    Lear
    0.52
    Mur
    0.52
    A
    0.52
    Primitive
    0.50
    “
    0.50
    MUR
    0.48
     pumpkin
    0.48
    ...),
    0.47
     fish
    0.47
    POSITIVE LOGITS
     Noeud
    0.54
     TypeScript
    0.53
     **/
    0.52
     ചെയ്
    0.51
     Hvis
    0.51
     ؛
    0.50
    涘
    0.49
    
    0.48
     fonctionnalités
    0.48
     estudos
    0.48
    Activations Density 0.000%

    No Known Activations