© 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. 248527
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     book
    0.53
     Idaho
    0.45
     evaluate
    0.44
     adopt
    0.41
     книга
    0.40
     l
    0.40
    ancial
    0.40
    雇
    0.40
    book
    0.39
     லா
    0.39
    POSITIVE LOGITS
    Matter
    0.43
     implies
    0.42
    implies
    0.42
    USES
    0.41
    Utilization
    0.41
     misused
    0.40
     mostró
    0.40
    Face
    0.39
     gezeigt
    0.39
    understood
    0.39
    Activations Density 0.000%

    No Known Activations