© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8806
    Prev
    Next
    INDEX
    Explanations

    certain type, from landmark

    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
     Priya
    0.41
     Resp
    0.40
     Norway
    0.38
     Oslo
    0.37
     油
    0.36
     Az
    0.36
     Kirchhoff
    0.36
    PSC
    0.36
    abha
    0.36
     আমেরিক
    0.35
    POSITIVE LOGITS
    Lora
    0.39
    findpost
    0.39
     bày
    0.38
    ordin
    0.37
    ારા
    0.37
    墳
    0.37
    ərd
    0.37
     २४
    0.36
     सरदार
    0.36
     इस्ती
    0.35
    Activations Density 0.012%

    No Known Activations