© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200468
    Prev
    Next
    INDEX
    Explanations

    within limits

    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_46_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
     well
    2.58
    well
    2.28
     Well
    2.25
    Well
    2.22
     WELL
    1.91
    WELL
    1.81
     잘
    1.76
     bien
    1.72
     добре
    1.66
     хорошо
    1.60
    POSITIVE LOGITS
    (`/
    0.39
     отли
    0.39
    )^{*
    0.37
     `<=`
    0.37
    )\|
    0.36
    ㍉
    0.36
    ouli
    0.36
     hil
    0.35
     harsh
    0.34
     Cori
    0.34
    Activations Density 0.101%

    No Known Activations