© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107999
    Prev
    Next
    INDEX
    Explanations

    yes, ye, yo

    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_1_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
     to
    1.71
     at
    1.35
     that
    1.13
    もの
    1.12
    {
    1.09
    ように
    1.05
    中で
    1.03
    場合の
    1.02
    ]
    1.02
    ある
    1.01
    POSITIVE LOGITS
    ä
    1.23
    1.14
    á
    1.13
     a
    0.98
    is
    0.84
    ip
    0.82
    ًا
    0.81
    Name
    0.80
     व
    0.79
     а
    0.79
    Activations Density 0.000%

    No Known Activations