© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46582
    Prev
    Next
    INDEX
    Explanations

    applying for admission or extensions

    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
    फ्ट
    0.46
    בר
    0.44
    媚
    0.44
    Api
    0.42
     lakukan
    0.42
    ৮
    0.41
     finito
    0.40
     மெட்ரோ
    0.40
    გრ
    0.39
    ]]$
    0.39
    POSITIVE LOGITS
    chende
    0.48
    uncie
    0.43
    emitting
    0.42
    ല്ലാം
    0.41
    知道
    0.41
     pursuit
    0.41
    吆
    0.41
    ્ટ
    0.40
     promote
    0.40
     absence
    0.40
    Activations Density 0.010%

    No Known Activations