© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121112
    Prev
    Next
    INDEX
    Explanations

    sister, granddaughter

    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_27_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
     வேண்ட
    0.31
     危
    0.30
    ADING
    0.30
    GD
    0.29
    ampionship
    0.29
     пользова
    0.29
    issner
    0.29
    gebnisse
    0.29
     уто
    0.29
     इच्छ
    0.29
    POSITIVE LOGITS
    িগ্ন
    0.38
    міну
    0.36
    মিন
    0.35
    median
    0.33
    वे
    0.33
    keySet
    0.32
    ♤
    0.32
     tuvo
    0.31
    तालों
    0.30
    आती
    0.30
    Activations Density 0.000%

    No Known Activations