© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226828
    Prev
    Next
    INDEX
    Explanations

    relative positioning

    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_6_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
    2
    1.30
    u
    0.96
    OK
    0.93
     transistor
    0.92
     defin
    0.91
    s
    0.89
    3
    0.87
    4
    0.86
    5
    0.85
    OP
    0.84
    POSITIVE LOGITS
    𝓭
    1.15
    ون
    1.03
     inclinations
    1.03
    ت
    1.00
     Многие
    1.00
    प
    0.99
     minimising
    0.98
    두
    0.97
     academics
    0.96
    न
    0.95
    Activations Density 0.002%

    No Known Activations