© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38785
    Prev
    Next
    INDEX
    Explanations

    iterating through items

    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_57_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
    Eksterne
    0.43
     Epoch
    0.40
     cadeira
    0.40
     Eber
    0.39
     э
    0.39
    សា
    0.39
     Teraz
    0.39
    áne
    0.38
    ểu
    0.38
     松
    0.38
    POSITIVE LOGITS
     number
    0.43
    number
    0.42
    ◑
    0.41
    kend
    0.35
     VG
    0.34
     multitude
    0.33
     RR
    0.33
     implied
    0.33
    </thead>
    0.32
    jud
    0.32
    Activations Density 0.001%

    No Known Activations