© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 229244
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ⠛
    0.38
     stakes
    0.38
     diferentes
    0.37
     combina
    0.36
     tert
    0.36
     aaa
    0.36
    米的
    0.35
    }}.
    0.35
     gah
    0.35
    日の
    0.34
    POSITIVE LOGITS
    loose
    0.38
     interessiert
    0.38
    chap
    0.38
     oldCount
    0.36
    кса
    0.36
    posti
    0.36
    placed
    0.35
    за
    0.35
    happ
    0.35
    ဆိုင်
    0.35
    Activations Density 0.000%

    No Known Activations