© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42738
    Prev
    Next
    INDEX
    Explanations

    VP9, AV1, H.264, H.265 codecs

    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_13_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
    чку
    0.55
    durationType
    0.53
    τε
    0.52
    чке
    0.52
     dupatta
    0.52
    ومات
    0.51
    σης
    0.50
    ք
    0.49
    }}
    0.49
     طور
    0.49
    POSITIVE LOGITS
     Observations
    0.53
     رائے
    0.53
    பல
    0.52
     Beware
    0.52
     Cinema
    0.50
     Observation
    0.50
     acknowledged
    0.49
     Caution
    0.48
    ᱧ
    0.48
     bernama
    0.48
    Activations Density 0.002%

    No Known Activations