© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141801
    Prev
    Next
    INDEX
    Explanations

    optimus, usus, highest

    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_12_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
    ˂
    0.57
    </i>
    0.54
    ˃
    0.54
    優れた
    0.52
     burdens
    0.51
    ್ರಿ
    0.51
    Ин
    0.50
     가진
    0.49
    ></
    0.48
     좋은
    0.48
    POSITIVE LOGITS
    ix
    0.56
    na
    0.54
    an
    0.53
    ot
    0.52
    ane
    0.52
     terzo
    0.52
    ay
    0.51
    ut
    0.51
    ort
    0.51
    no
    0.50
    Activations Density 0.036%

    No Known Activations