© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208199
    Prev
    Next
    INDEX
    Explanations

    return or error handling

    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_25_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
    𝙧
    0.37
    を用
    0.36
    денти
    0.36
     nasc
    0.36
    ruar
    0.35
    මි
    0.35
     categ
    0.35
     afford
    0.35
    ñar
    0.34
    Substituting
    0.34
    POSITIVE LOGITS
    acije
    0.38
    apikey
    0.37
    轰
    0.37
     একসাথে
    0.36
     .......
    0.35
    之间
    0.35
     ...)
    0.35
     razem
    0.35
     wykon
    0.34
    一场
    0.34
    Activations Density 0.005%

    No Known Activations