© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 106435
    Prev
    Next
    INDEX
    Explanations

    Office software

    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_44_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
    𒍪
    0.38
    ܘ
    0.36
    繇
    0.36
     পারব
    0.36
    рун
    0.36
    ８
    0.36
    בּ
    0.36
    utis
    0.35
     Reverso
    0.35
    aderos
    0.35
    POSITIVE LOGITS
    plus
    0.36
    啸
    0.36
     Rxf
    0.35
     lợi
    0.35
    cement
    0.35
     bursting
    0.35
    categorical
    0.35
    Fifth
    0.35
     infusions
    0.35
    му
    0.35
    Activations Density 0.000%

    No Known Activations