© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41915
    Prev
    Next
    INDEX
    Explanations

    describe instances

    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_22_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
     scissor
    0.46
     scissors
    0.46
    룺
    0.46
    Неза
    0.44
    ستين
    0.44
     করিয়৷
    0.44
     рука
    0.41
    𐱅
    0.41
    磷
    0.40
    橛
    0.40
    POSITIVE LOGITS
     includes
    0.42
     crowded
    0.41
     hundred
    0.41
    atel
    0.41
     nume
    0.39
     १
    0.39
     welcome
    0.38
    defini
    0.38
    mara
    0.38
    emi
    0.38
    Activations Density 0.000%

    No Known Activations