© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168673
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     typically
    0.53
    typically
    0.47
    嘅
    0.44
     của
    0.43
     bakal
    0.42
    Typically
    0.41
     खासियत
    0.40
     bonds
    0.40
    簽
    0.40
     Typically
    0.40
    POSITIVE LOGITS
     Goes
    0.50
    它的
    0.44
     무엇
    0.43
    他们的
    0.42
     hva
    0.42
     находится
    0.41
     कोणत्या
    0.41
     goes
    0.41
    ходит
    0.41
    падает
    0.41
    Activations Density 0.000%

    No Known Activations