© 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. 48435
    Prev
    Next
    INDEX
    Explanations

    bounce back from setbacks

    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
     solu
    0.37
     issues
    0.35
     توص
    0.33
    웅
    0.33
     corner
    0.32
     proudly
    0.32
    issues
    0.32
    verte
    0.32
     alternative
    0.32
     Verte
    0.32
    POSITIVE LOGITS
     emocional
    0.41
     microfiber
    0.38
     Tops
    0.38
     PMS
    0.37
     двигателя
    0.36
    셜
    0.35
    袜子
    0.35
     gelangen
    0.35
     misfortune
    0.35
     दै
    0.34
    Activations Density 0.010%

    No Known Activations