© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200111
    Prev
    Next
    INDEX
    Explanations

    recover recovery

    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_50_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
     Duran
    0.41
     Zet
    0.39
     近
    0.37
     коре
    0.37
    ゾ
    0.37
    ментов
    0.37
    Aaron
    0.36
    कांना
    0.36
    こ
    0.35
    As
    0.35
    POSITIVE LOGITS
     recovered
    1.58
     recover
    1.55
     recovery
    1.55
     recovering
    1.48
     Recovery
    1.45
     recuper
    1.45
     Recover
    1.45
    recovered
    1.45
    Recover
    1.44
    Recovery
    1.41
    Activations Density 0.001%

    No Known Activations