© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111244
    Prev
    Next
    INDEX
    Explanations

    losing bladder, weight, grip, details

    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_2_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
    on
    1.51
    a
    1.38
    are
    1.13
    ew
    1.05
    to
    1.04
    around
    1.04
    all
    1.03
    ari
    1.00
    elm
    0.99
    /
    0.99
    POSITIVE LOGITS
    ش
    1.30
    ）；
    1.30
    یا
    1.20
    ین
    1.12
    اني
    1.09
    л
    1.02
    м
    1.02
    <0x80>
    1.01
    写
    1.01
    기
    0.98
    Activations Density 0.000%

    No Known Activations