© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177625
    Prev
    Next
    INDEX
    Explanations

    just paste or copy

    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_24_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
     mellom
    0.35
     pescado
    0.33
     altına
    0.33
     nye
    0.33
    ㉖
    0.33
     mellem
    0.32
     lenguaje
    0.32
    鍊
    0.32
     ws
    0.31
    កាន់
    0.31
    POSITIVE LOGITS
    Equals
    0.31
    companions
    0.30
    Rag
    0.29
     survivors
    0.28
     दत्त
    0.27
     دام
    0.27
    screenshot
    0.27
    හර
    0.27
    Seperti
    0.27
    SW
    0.26
    Activations Density 0.014%

    No Known Activations