© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175576
    Prev
    Next
    INDEX
    Explanations

    html head

    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_24_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
    钿
    0.42
     forte
    0.39
     larga
    0.38
     avail
    0.37
     philosophy
    0.37
    Dial
    0.37
    桻
    0.37
     riser
    0.36
    旿
    0.36
     behavioral
    0.36
    POSITIVE LOGITS
     초기
    0.39
    ESTIC
    0.37
     初始化
    0.37
     المب
    0.37
    初步
    0.37
    mathrm
    0.36
    eyen
    0.36
     初期
    0.36
    Environment
    0.35
    toolkit
    0.34
    Activations Density 0.000%

    No Known Activations