© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219098
    Prev
    Next
    INDEX
    Explanations

    beach destinations and clubs

    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_31_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
     Bacter
    0.36
     মহা
    0.34
    busch
    0.33
     पर्स
    0.33
     დ
    0.33
     recognisable
    0.33
    igné
    0.33
     तरल
    0.32
     புற
    0.32
     dokumen
    0.32
    POSITIVE LOGITS
     productivity
    0.40
    productivity
    0.38
    
    0.37
    ือก
    0.36
    Moss
    0.35
    ouss
    0.34
     ভারতীয়
    0.34
     Endangered
    0.34
    Range
    0.34
     Productivity
    0.34
    Activations Density 0.010%

    No Known Activations