© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199577
    Prev
    Next
    INDEX
    Explanations

    dynamic impulse

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    اعد
    0.47
    োয়ার
    0.39
    Pix
    0.36
    REETYPE
    0.36
    賈
    0.36
     Tha
    0.36
    ندگان
    0.36
    形で
    0.36
    宜
    0.36
    ष्
    0.35
    POSITIVE LOGITS
    combination
    0.40
     rolls
    0.40
    ่อง
    0.38
    dynamic
    0.38
    performance
    0.37
     Impulse
    0.36
    track
    0.36
     Dynamic
    0.36
     dynamic
    0.35
     impulse
    0.34
    Activations Density 0.000%

    No Known Activations