© 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
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248727
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
     \"
    0.57
     «
    0.51
     \|
    0.47
    $)
    0.42
     ``
    0.41
     “
    0.41
     "/")
    0.41
     |
    0.40
     ".")
    0.40
    archiwizowane
    0.39
    POSITIVE LOGITS
    ’?
    0.54
    ’;
    0.48
    ’!
    0.46
    ?’
    0.46
    …’
    0.43
    ’,
    0.41
    .’
    0.40
    ΄
    0.39
     inc
    0.38
     embarrass
    0.38
    Activations Density 0.001%

    No Known Activations