© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53860
    Prev
    Next
    INDEX
    Explanations

    descriptive labels

    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_30_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
     PLUS
    0.46
     YEAR
    0.41
     प्लस
    0.41
    ertung
    0.39
     క
    0.39
     vermeiden
    0.39
     플러스
    0.39
     ຮ
    0.38
     합동
    0.38
    铛
    0.38
    POSITIVE LOGITS
     ചെയ്ത
    0.40
    specified
    0.35
    Andrea
    0.35
    Aren
    0.35
    処
    0.35
    ()}')
    0.34
     Aren
    0.34
    Setter
    0.34
    means
    0.34
     тол
    0.34
    Activations Density 0.052%

    No Known Activations