© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53049
    Prev
    Next
    INDEX
    Explanations

    job skills and systems

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     bookcases
    0.42
    𒂍
    0.40
    uhe
    0.40
     zatem
    0.37
     adherents
    0.36
     RETURNS
    0.36
     dość
    0.36
    OfDeath
    0.35
     theseKeys
    0.35
    uern
    0.35
    POSITIVE LOGITS
    BL
    0.48
    ||
    0.48
     det
    0.46
     BL
    0.46
     wh
    0.45
     w
    0.43
    Launching
    0.42
    [
    0.42
     Det
    0.41
    WH
    0.40
    Activations Density 0.004%

    No Known Activations