© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61368
    Prev
    Next
    INDEX
    Explanations

    baby talk

    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_11_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
     الَّذ
    0.52
    ﻞ
    0.50
    λης
    0.50
     콜
    0.50
    ἢ
    0.49
     ܠ
    0.49
    趨
    0.49
    حي
    0.48
     contrace
    0.48
     prostitute
    0.48
    POSITIVE LOGITS
     Emirates
    0.48
    Fragmentation
    0.48
    IA
    0.46
    Absorption
    0.46
     Badminton
    0.44
    Kansas
    0.43
    ld
    0.42
     With
    0.42
    </h4>
    0.41
    行政
    0.41
    Activations Density 0.000%

    No Known Activations