© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45796
    Prev
    Next
    INDEX
    Explanations

    crash, disqualification, reliability

    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_13_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
     crumble
    0.25
    墺
    0.25
     trout
    0.23
     crumbling
    0.23
    स्ट
    0.22
     bombard
    0.22
     tunic
    0.22
     maestro
    0.21
     crumb
    0.21
     registrar
    0.21
    POSITIVE LOGITS
    ли
    0.21
    ви
    0.21
    矨
    0.21
    tolower
    0.20
    ма
    0.20
    common
    0.20
    ondere
    0.20
    埆
    0.20
    always
    0.19
    sampling
    0.19
    Activations Density 0.002%

    No Known Activations