© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66336
    Prev
    Next
    INDEX
    Explanations

    Ta

    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_51_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
    ्व
    0.42
     वा
    0.41
    МИ
    0.40
     scut
    0.40
    Shutdown
    0.40
    rasp
    0.39
    冧
    0.39
    ラム
    0.38
    Melissa
    0.38
    amit
    0.38
    POSITIVE LOGITS
    бурге
    0.39
     patriarchal
    0.38
     Moses
    0.38
     afro
    0.38
    ARO
    0.38
     androgen
    0.37
     oddly
    0.37
     aro
    0.37
    getEntity
    0.37
     odd
    0.37
    Activations Density 0.000%

    No Known Activations