© 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. 244848
    Prev
    Next
    INDEX
    Explanations

    install libraries

    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
    ို့
    0.37
    cnt
    0.35
    IMPORTANT
    0.35
    Important
    0.35
    Open
    0.34
    Let
    0.33
     conduction
    0.32
    옴
    0.32
     دہ
    0.32
    Skip
    0.32
    POSITIVE LOGITS
     जीवा
    0.43
    ancio
    0.42
     rat
    0.41
     Rat
    0.40
    ര്യ
    0.40
     рыба
    0.40
    শিক
    0.39
     Municipal
    0.38
    raints
    0.38
    ivities
    0.38
    Activations Density 0.002%

    No Known Activations