© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208171
    Prev
    Next
    INDEX
    Explanations

    need

    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_10_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
    <0x80>
    0.80
    ườn
    0.76
    ння
    0.72
    www
    0.71
     ứng
    0.71
    ૦
    0.71
     udvik
    0.68
    𝐩
    0.68
    𝕣
    0.68
     පිළ
    0.68
    POSITIVE LOGITS
     to
    1.52
     need
    1.34
    ل
    1.23
    ي
    1.16
    i
    1.16
    us
    1.09
    need
    1.06
    י
    1.05
    AG
    1.04
    in
    1.02
    Activations Density 0.005%

    No Known Activations