© 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. 23627
    Prev
    Next
    INDEX
    Explanations

    say "h" words

    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
     foo
    0.43
    ngthen
    0.40
     തുടർ
    0.40
    ಮೆ
    0.40
     leveled
    0.37
     them
    0.37
     virt
    0.36
     ``
    0.36
     ket
    0.36
     BUN
    0.36
    POSITIVE LOGITS
    Ссы
    0.52
    Consistent
    0.47
     seiner
    0.41
    Their
    0.41
    觟
    0.40
     Ее
    0.39
    #(
    0.39
    consistent
    0.38
    Ử
    0.38
    Drama
    0.37
    Activations Density 0.001%

    No Known Activations