© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154290
    Prev
    Next
    INDEX
    Explanations

    proven track record

    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_23_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
    พ
    0.44
     معظم
    0.41
     Polymer
    0.37
    擁有
    0.37
    ల
    0.36
     স্বয়ং
    0.36
    Continuous
    0.36
    getItemId
    0.36
    typeof
    0.36
    πος
    0.36
    POSITIVE LOGITS
    ählte
    0.45
     २०
    0.44
    asinya
    0.44
    ത്തോടെ
    0.44
     <=
    0.43
     certaine
    0.42
     signer
    0.42
    izontal
    0.41
    abling
    0.41
    ersi
    0.41
    Activations Density 0.000%

    No Known Activations