© 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. 167160
    Prev
    Next
    INDEX
    Explanations

    output account data

    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
    承
    0.40
     Great
    0.39
    عيه
    0.39
    onomics
    0.38
    控
    0.38
    Franco
    0.38
    般
    0.38
    sho
    0.37
    烣
    0.37
    Stabil
    0.37
    POSITIVE LOGITS
     Am
    0.59
    Am
    0.46
     am
    0.45
     output
    0.45
     Long
    0.42
     Output
    0.42
     Account
    0.42
     accounts
    0.42
     account
    0.41
     accounted
    0.39
    Activations Density 0.003%

    No Known Activations