© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76237
    Prev
    Next
    INDEX
    Explanations

    definitely followed by assessments

    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_31_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
    ዛ
    0.41
    raintes
    0.38
    힌
    0.37
    芜
    0.36
     विरा
    0.36
     mutlaka
    0.36
     Contains
    0.36
    Kings
    0.36
    Py
    0.35
     یہی
    0.35
    POSITIVE LOGITS
    turbo
    0.42
     সম্ভবত
    0.40
    actually
    0.40
    jackson
    0.37
    ৎ
    0.37
    jupiter
    0.37
     laryng
    0.36
     registrazione
    0.35
    intelligence
    0.35
    appointed
    0.35
    Activations Density 0.003%

    No Known Activations