© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12335
    Prev
    Next
    INDEX
    Explanations

    stakeholder relationships and 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_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
    상이
    0.47
     Souls
    0.45
    |
    0.44
    É
    0.44
     entier
    0.44
    ™,
    0.43
    VIEWS
    0.42
    여행
    0.42
    कब
    0.41
    ATORY
    0.41
    POSITIVE LOGITS
    emm
    0.48
    𝘭
    0.47
    janja
    0.47
    duk
    0.44
    wa
    0.44
    mask
    0.44
     Nähe
    0.43
    ześnie
    0.43
    ze
    0.43
    mason
    0.43
    Activations Density 0.009%

    No Known Activations