© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 252278
    Prev
    Next
    INDEX
    Explanations

    self

    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
    )_
    0.40
    .):
    0.38
    )^
    0.38
     abband
    0.37
     एमएस
    0.37
    .)
    0.36
     MS
    0.36
    )=(\
    0.36
    ion
    0.36
    ...)
    0.36
    POSITIVE LOGITS
     barrio
    0.38
     //!
    0.37
    회가
    0.36
    efois
    0.36
     Across
    0.36
     හැකිය
    0.36
    Across
    0.35
    써
    0.35
    োট
    0.35
     across
    0.34
    Activations Density 0.002%

    No Known Activations