© 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. 84233
    Prev
    Next
    INDEX
    Explanations

    file, line, fail, kubernetes

    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
     mettre
    0.43
    </h3>
    0.42
    <h3>
    0.41
    sure
    0.41
    /
    0.40
     verhaal
    0.38
    '
    0.38
    찧
    0.38
    \
    0.38
     Okla
    0.38
    POSITIVE LOGITS
    বিষয়
    0.40
     causative
    0.39
     bezier
    0.38
     cartera
    0.38
     bxa
    0.38
     sx
    0.37
     binders
    0.37
     bm
    0.37
     گی
    0.37
     vocabulary
    0.36
    Activations Density 0.001%

    No Known Activations