© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14335
    Prev
    Next
    INDEX
    Explanations

    well good welcome

    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_34_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
     adjusting
    0.42
    
    0.38
    jà
    0.37
     validInput
    0.37
     adjustments
    0.36
    所需的
    0.36
    幅広い
    0.36
    躁
    0.36
     deserves
    0.35
     quantities
    0.35
    POSITIVE LOGITS
    pgamma
    0.42
     विभा
    0.38
    imm
    0.37
     ire
    0.37
    สัง
    0.37
    łada
    0.37
     san
    0.36
    ittaa
    0.35
    𝙰
    0.35
     im
    0.35
    Activations Density 0.562%

    No Known Activations