© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130699
    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_25_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
    `,
    0.50
     longitud
    0.48
     Hub
    0.47
     leia
    0.45
     Hoss
    0.44
    debugger
    0.44
     spender
    0.43
     Kit
    0.43
    }})
    0.43
     Parque
    0.43
    POSITIVE LOGITS
     істори
    0.50
    ᒫ
    0.49
    विज्ञान
    0.47
    वर्ल्ड
    0.47
    ध्या
    0.46
    တွင်
    0.46
    іб
    0.46
    iją
    0.45
    க
    0.45
    ध्ये
    0.44
    Activations Density 0.000%

    No Known Activations