© 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. 167104
    Prev
    Next
    INDEX
    Explanations

    dashes

    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
    
    0.39
    puls
    0.37
    -:
    0.35
     aggravating
    0.34
    accuracy
    0.33
     padre
    0.33
    Avoid
    0.33
    -”
    0.33
    inephrine
    0.33
    that
    0.32
    POSITIVE LOGITS
     وتب
    0.43
     تب
    0.38
     Punkten
    0.38
    Tab
    0.36
     tab
    0.36
    abei
    0.36
     Punkte
    0.34
    "—
    0.34
     —¿
    0.34
    }~\
    0.34
    Activations Density 0.000%

    No Known Activations