© 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
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 197048
    Prev
    Next
    INDEX
    Explanations

    give you

    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
    ärt
    0.41
    ötz
    0.40
    ñas
    0.40
    arbeitung
    0.39
    ፂ
    0.39
    बंध
    0.38
    yfikacji
    0.38
    ovič
    0.37
    ènes
    0.37
     atténuées
    0.37
    POSITIVE LOGITS
     ador
    0.41
      
    0.40
     garantiza
    0.39
     enunci
    0.39
     buton
    0.38
     Bioinformatics
    0.38
     Button
    0.37
     garante
    0.37
     inti
    0.37
     I
    0.37
    Activations Density 0.005%

    No Known Activations