© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 214733
    Prev
    Next
    INDEX
    Explanations

    git clone

    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_16_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
    K
    0.61
     П
    0.56
     c
    0.55
    will
    0.54
    times
    0.54
    N
    0.54
    ke
    0.53
    recated
    0.53
     предполага
    0.52
     d
    0.52
    POSITIVE LOGITS
     visceral
    0.52
    ્યુ
    0.51
    گن
    0.51
    篂
    0.51
    شو
    0.49
    álisis
    0.49
    હુ
    0.49
     centerX
    0.48
     Endocrinol
    0.47
    腈
    0.47
    Activations Density 0.003%

    No Known Activations