© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150524
    Prev
    Next
    INDEX
    Explanations

    OCR errors

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     u
    1.34
    u
    1.20
    ｕ
    1.17
    U
    1.14
    𝘂
    1.13
    uf
    1.13
    ud
    1.12
    uc
    1.11
    𝚞
    1.09
    𝙪
    1.07
    POSITIVE LOGITS
    Fl
    0.46
    fs
    0.42
    Ft
    0.42
    ft
    0.41
    fpr
    0.41
    fq
    0.40
    fo
    0.40
    <0x86>
    0.39
    FQ
    0.39
    Fs
    0.39
    Activations Density 0.000%

    No Known Activations