© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42244
    Prev
    Next
    INDEX
    Explanations

    revised version

    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_3_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
    _
    0.63
    anda
    0.62
    acara
    0.60
    I
    0.59
    nd
    0.58
    awning
    0.56
    '
    0.55
    was
    0.55
    thal
    0.55
    ant
    0.54
    POSITIVE LOGITS
     on
    0.96
     is
    0.92
    on
    0.80
    り
    0.64
     swirl
    0.63
    冰
    0.63
    ﾘ
    0.63
    ี
    0.62
     খাই
    0.61
    甠
    0.61
    Activations Density 0.003%

    No Known Activations