© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42658
    Prev
    Next
    INDEX
    Explanations

    QUESTION markers

    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_22_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
     Bolo
    0.42
    賛
    0.41
    </h2>
    0.39
    彼の
    0.39
     insurgents
    0.39
    彼
    0.39
     shipper
    0.39
     Athena
    0.38
     autorités
    0.38
     supérieure
    0.38
    POSITIVE LOGITS
    茦
    0.42
    ترك
    0.41
    炡
    0.41
    丽
    0.40
    Tarjeta
    0.39
     тексти
    0.39
    খিক
    0.38
    睃
    0.38
    trimethyl
    0.38
     PHILLIPS
    0.38
    Activations Density 0.000%

    No Known Activations