© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38872
    Prev
    Next
    INDEX
    Explanations

    find synonyms

    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_57_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
    ेशन
    0.49
    ização
    0.43
    仃
    0.41
    되기
    0.38
    стан
    0.38
    แนะนำ
    0.38
    uiu
    0.38
    சனம்
    0.37
     எதிர்ப
    0.37
    ⤦
    0.37
    POSITIVE LOGITS
    en
    1.06
    EN
    0.75
    ene
    0.64
    ens
    0.61
    enf
    0.54
    ən
    0.54
    enb
    0.53
    ен
    0.51
    েন
    0.50
    erna
    0.49
    Activations Density 0.002%

    No Known Activations