© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208020
    Prev
    Next
    INDEX
    Explanations

    discovery requests

    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_25_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
    䐂
    0.38
     wherever
    0.37
     affirm
    0.37
     forcefully
    0.36
    Loving
    0.35
    ᖁ
    0.35
     ära
    0.35
    لوں
    0.35
    妛
    0.35
     جائے
    0.34
    POSITIVE LOGITS
     труда
    0.46
     myfile
    0.40
    భ్య
    0.39
    彡
    0.38
     BAU
    0.38
    ㅑ
    0.38
     CNR
    0.37
     INR
    0.37
     Đài
    0.37
     EOS
    0.36
    Activations Density 0.000%

    No Known Activations