© 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. 207200
    Prev
    Next
    INDEX
    Explanations

    say punctuation

    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
     }>;
    0.53
    촉
    0.40
    ".$
    0.39
     }}">
    0.38
    ")):
    0.38
     Tattha
    0.38
     ['$
    0.38
    塬
    0.37
    actionMode
    0.37
    coelastic
    0.36
    POSITIVE LOGITS
    )(
    0.96
    )(
    0.88
    }(
    0.85
    ).(
    0.81
     ())
    0.77
    }(\
    0.77
     )(
    0.77
    )(\
    0.75
    ”(
    0.75
    」(
    0.74
    Activations Density 0.010%

    No Known Activations