© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228700
    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
     almonds
    0.39
    datum
    0.37
     halve
    0.36
     surfboard
    0.36
    unders
    0.36
    𝙍
    0.35
     hs
    0.34
    ㄋ
    0.34
     zá
    0.34
    itr
    0.34
    POSITIVE LOGITS
     Professional
    0.42
    Professional
    0.41
     Place
    0.40
    }}/
    0.38
    Place
    0.38
     Defensa
    0.38
    ipelago
    0.38
    两年
    0.37
     chữa
    0.37
     Perception
    0.37
    Activations Density 0.000%

    No Known Activations