© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101546
    Prev
    Next
    INDEX
    Explanations

    velocity

    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_14_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
     그는
    0.67
    滏
    0.63
    滹
    0.63
    ቿ
    0.63
    ദീ
    0.60
     klingt
    0.59
     échantillons
    0.55
    摄像头
    0.55
     antiguas
    0.55
     ヨ
    0.54
    POSITIVE LOGITS
     time
    0.56
     ORNL
    0.48
     necessarily
    0.47
     -
    0.46
    ．
    0.46
    0.46
    щает
    0.45
     neural
    0.45
    上海
    0.44
     Hackney
    0.44
    Activations Density 0.000%

    No Known Activations