© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36375
    Prev
    Next
    INDEX
    Explanations

    soak up

    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_11_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
    ARE
    0.72
     эф
    0.67
    нуть
    0.65
    ﺎ
    0.64
    нула
    0.63
    ną
    0.61
    𝒐
    0.60
    ߋ
    0.60
    beitet
    0.59
    ﺖ
    0.59
    POSITIVE LOGITS
    an
    0.71
     taxi
    0.59
    ;
    0.55
     arbor
    0.54
     .
    0.53
     motion
    0.52
     apparition
    0.50
    man
    0.49
     axios
    0.49
    es
    0.49
    Activations Density 0.000%

    No Known Activations