© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 214949
    Prev
    Next
    INDEX
    Explanations

    gradually

    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_16_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
    ㄺ
    0.54
     えっと
    0.54
    렜
    0.50
    ınız
    0.50
    }.",
    0.49
    께서
    0.49
    inizin
    0.49
    の結果
    0.48
    条例
    0.48
    attho
    0.47
    POSITIVE LOGITS
     (
    0.52
     VU
    0.44
    0
    0.44
     B
    0.43
     contender
    0.43
    <h2>
    0.43
     piccola
    0.43
     one
    0.42
     $
    0.42
     riman
    0.42
    Activations Density 0.000%

    No Known Activations