© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34311
    Prev
    Next
    INDEX
    Explanations

    rasped

    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_50_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
    ודי
    0.44
    ou
    0.42
    udian
    0.42
    ુલ
    0.40
    ab
    0.39
    纡
    0.39
    TA
    0.38
    aud
    0.38
    ኩ
    0.38
    ாவின்
    0.38
    POSITIVE LOGITS
    সম
    0.46
     डॉक्यूमेंट
    0.41
    ^*_{
    0.39
    窄
    0.38
    autoprefixer
    0.38
     LDGs
    0.37
    𝒋
    0.37
     Artificial
    0.37
    ikes
    0.36
    辣
    0.36
    Activations Density 0.001%

    No Known Activations