© 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
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22550
    Prev
    Next
    INDEX
    Explanations

    How

    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
    --
    0.50
     avez
    0.43
    вя
    0.42
     have
    0.41
    —
    0.38
    ager
    0.38
     eager
    0.38
     имеют
    0.38
     --
    0.38
     HAVE
    0.37
    POSITIVE LOGITS
    üns
    0.40
     finds
    0.40
    પે
    0.37
     considers
    0.37
     fair
    0.37
    ámicas
    0.37
     Struct
    0.36
    𒁹
    0.36
    Thing
    0.35
     Finds
    0.35
    Activations Density 0.002%

    No Known Activations