© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89440
    Prev
    Next
    INDEX
    Explanations

    nginx sites configuration

    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_23_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
     Γ
    0.40
    </th>
    0.38
    消防
    0.38
    鎵
    0.36
     Hermitian
    0.36
     x
    0.36
     Fam
    0.35
    rangle
    0.35
     St
    0.35
     DMF
    0.35
    POSITIVE LOGITS
     новый
    0.46
     tracts
    0.45
    ᱾
    0.43
    驄
    0.43
     склады
    0.42
    㶪
    0.42
    тку
    0.41
     режим
    0.41
    坵
    0.41
    ㇁
    0.41
    Activations Density 0.000%

    No Known Activations