© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167105
    Prev
    Next
    INDEX
    Explanations

    say "w" 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
    Me
    0.59
     Me
    0.57
     me
    0.50
    めに
    0.49
    め
    0.49
     ме
    0.48
    me
    0.45
    ಮೆ
    0.44
    めた
    0.44
    めて
    0.43
    POSITIVE LOGITS
     w
    0.51
     au
    0.40
     للح
    0.38
    夂
    0.38
    :],
    0.37
     Au
    0.37
    ວ
    0.37
    ται
    0.37
     tedy
    0.37
    इसमें
    0.37
    Activations Density 0.000%

    No Known Activations