© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 251083
    Prev
    Next
    INDEX
    Explanations

    Verse

    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_56_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
    causes
    0.40
    สอน
    0.38
    ‏:‏
    0.38
    аны
    0.37
     म्हण
    0.37
    paro
    0.36
    קה
    0.36
     teaching
    0.35
    ல்க
    0.35
    :‏
    0.35
    POSITIVE LOGITS
    )")
    0.49
    *)(
    0.46
     ...)
    0.46
    +-
    0.44
     disc
    0.44
    ^{*}$-
    0.42
    )^*
    0.42
    ³.
    0.40
    ³)
    0.40
    ())+
    0.40
    Activations Density 0.001%

    No Known Activations