© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80936
    Prev
    Next
    INDEX
    Explanations

    approaching her

    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_31_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
     acoustics
    0.39
    alike
    0.39
     goats
    0.38
    噺
    0.38
     tonnes
    0.38
     auditorium
    0.38
    ichtet
    0.37
    stability
    0.37
    リリース
    0.37
    assa
    0.36
    POSITIVE LOGITS
    abileceğ
    0.40
    জাল
    0.37
    Group
    0.36
     vaga
    0.36
    जोन
    0.36
    휀
    0.35
     encuentros
    0.34
    Drain
    0.34
    蹂
    0.34
     perc
    0.34
    Activations Density 0.039%

    No Known Activations