© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12758
    Prev
    Next
    INDEX
    Explanations

    sprinklered?, alarms?, update

    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_40_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
     Objection
    0.40
    ጀት
    0.40
     ರೂಪ
    0.40
     remarque
    0.38
     खातों
    0.38
    раста
    0.38
    đena
    0.38
    ὀ
    0.36
    Ό
    0.35
     الدرا
    0.35
    POSITIVE LOGITS
     தக
    0.37
    msgSender
    0.36
     perch
    0.35
    Shadow
    0.35
    ïd
    0.35
    proficiency
    0.34
     shroud
    0.34
     Aham
    0.34
    thon
    0.34
     stratosphere
    0.34
    Activations Density 0.040%

    No Known Activations