© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197088
    Prev
    Next
    INDEX
    Explanations

    line-height: 1.6

    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_26_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
     roasting
    0.42
    itness
    0.40
     Rt
    0.40
    \"]\
    0.38
     flagged
    0.38
     Purposes
    0.37
     BlogPost
    0.37
     flagging
    0.37
     Preventing
    0.37
     Experience
    0.37
    POSITIVE LOGITS
    艙
    0.41
     دائما
    0.40
    म्मू
    0.39
    ábban
    0.39
     êtres
    0.38
    뭡
    0.38
    ユニット
    0.37
    ワード
    0.37
    ிருக்க
    0.36
    íamos
    0.36
    Activations Density 0.000%

    No Known Activations