© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 169777
    Prev
    Next
    INDEX
    Explanations

    say ".*" or "." chars

    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
     '').
    0.40
    #
    0.38
    ).</
    0.37
    ".[
    0.36
    њима
    0.36
    诘
    0.35
    ).[
    0.35
    }$.)
    0.34
    ')}>
    0.34
    POSITIVE LOGITS
     HIGH
    0.44
     AS
    0.42
    ::
    0.42
     as
    0.39
     کس
    0.39
     won
    0.38
     }
    0.37
     INTO
    0.37
    ]::
    0.37
     HAVING
    0.36
    Activations Density 0.001%

    No Known Activations