© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215493
    Prev
    Next
    INDEX
    Explanations

    interface and connection setup

    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_31_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
     success
    0.39
     sukses
    0.38
     slimmer
    0.37
     pronounce
    0.36
     categor
    0.36
    क्सर
    0.35
     若
    0.35
     पतला
    0.34
     분류
    0.34
     conservative
    0.34
    POSITIVE LOGITS
    Hat
    0.41
    мот
    0.40
    ORE
    0.40
    Her
    0.39
    Curs
    0.38
    詆
    0.38
     தரி
    0.38
    cary
    0.37
    Mode
    0.37
    Away
    0.37
    Activations Density 0.000%

    No Known Activations