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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6993
    Prev
    Next
    INDEX
    Explanations

    enjoy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     ช่วย
    0.39
    ủ
    0.39
     helping
    0.39
     choosing
    0.39
    喝酒
    0.37
    gares
    0.37
     olhando
    0.36
     assisting
    0.36
    }+(\
    0.36
    道理
    0.35
    POSITIVE LOGITS
     கண்டி
    0.34
    ாக்
    0.33
    Spend
    0.33
     Lindsay
    0.33
     PA
    0.33
    がございます
    0.32
     CORPORATION
    0.32
     stand
    0.32
    evaluation
    0.32
    графии
    0.32
    Activations Density 0.140%

    No Known Activations