© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176042
    Prev
    Next
    INDEX
    Explanations

    control signals for processes

    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_24_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
     os
    0.09
     TAS
    0.09
    Organ
    0.08
     TS
    0.08
     ID
    0.08
     оцени
    0.08
     A
    0.08
     Organ
    0.08
     crist
    0.08
    TAS
    0.08
    POSITIVE LOGITS
     porttitor
    0.09
     ऊंचाई
    0.09
    }\!\
    0.09
    lapping
    0.09
    ポート
    0.09
    ลอด
    0.09
     quoique
    0.09
    觛
    0.09
     insanity
    0.08
     жесто
    0.08
    Activations Density 0.018%

    No Known Activations