© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197085
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    gué
    0.46
     FODC
    0.46
    ʌ
    0.42
    érience
    0.40
    ъек
    0.38
    gebäude
    0.38
    |।
    0.37
    nonpayable
    0.37
    érieur
    0.36
    দায়িক
    0.36
    POSITIVE LOGITS
     amongst
    0.40
     Other
    0.39
     Who
    0.38
     Left
    0.37
     Amongst
    0.37
     other
    0.37
     Paul
    0.36
     சேர்த்த
    0.36
     B
    0.35
     Memphis
    0.35
    Activations Density 0.001%

    No Known Activations