© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43925
    Prev
    Next
    INDEX
    Explanations

    blogging and bloggers

    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_13_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
    waste
    0.34
    m
    0.31
    0
    0.30
    riften
    0.30
    sp
    0.30
    es
    0.29
    benefits
    0.29
    p
    0.29
    b
    0.28
    et
    0.28
    POSITIVE LOGITS
     palco
    0.34
     modo
    0.32
     teórico
    0.30
     divor
    0.30
     pianist
    0.30
     venue
    0.30
     primeiro
    0.29
     optomet
    0.29
     endlich
    0.29
     *}$
    0.29
    Activations Density 0.005%

    No Known Activations