© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87310
    Prev
    Next
    INDEX
    Explanations

    OmniCorp Announces

    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_3_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
    و
    0.75
    ج
    0.71
    ل
    0.57
     বাঁচ
    0.55
     Paths
    0.55
    ম
    0.54
     कार्र
    0.54
     पंक्ति
    0.54
    터
    0.54
    }],
    0.54
    POSITIVE LOGITS
    :
    0.65
     narrated
    0.64
    il
    0.63
    im
    0.63
     legitim
    0.62
     categor
    0.60
    á
    0.59
    .
    0.58
     bajo
    0.57
     wielding
    0.55
    Activations Density 0.000%

    No Known Activations