© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175972
    Prev
    Next
    INDEX
    Explanations

    closed loop or path

    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_20_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
     nays
    0.26
     tease
    0.24
     attack
    0.24
     needlessly
    0.24
     embarrass
    0.23
    %);
    0.23
     unwilling
    0.23
     doub
    0.22
     対
    0.22
     unwillingness
    0.22
    POSITIVE LOGITS
    ﺸ
    0.22
    Filtered
    0.21
    pheromone
    0.20
    Drone
    0.20
    Junior
    0.20
    ﻬ
    0.20
     separar
    0.19
    成就
    0.19
    brightness
    0.19
    Flights
    0.18
    Activations Density 0.002%

    No Known Activations