© 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. 220626
    Prev
    Next
    INDEX
    Explanations

    phrases connecting business functions

    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
    bsen
    0.40
    ัคร
    0.38
    ྩ
    0.38
    ᕆ
    0.38
    ศึกษา
    0.37
    FindBy
    0.37
     averigu
    0.36
     seduce
    0.36
    tection
    0.36
    icoes
    0.36
    POSITIVE LOGITS
    衹
    0.39
     condominium
    0.39
    深圳市
    0.38
     Inns
    0.37
     witness
    0.35
     Toast
    0.35
     Condo
    0.35
    hak
    0.35
     Witnesses
    0.35
     Condition
    0.35
    Activations Density 0.001%

    No Known Activations