© 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. 213663
    Prev
    Next
    INDEX
    Explanations

    scientific names

    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
     O
    0.52
     Marty
    0.44
     রাহ
    0.43
     Gillespie
    0.42
     Martel
    0.42
    앰
    0.40
     Kiel
    0.40
    drug
    0.40
    روی
    0.40
    >>)
    0.40
    POSITIVE LOGITS
    prong
    0.41
    Seven
    0.39
    ুজ
    0.38
     dro
    0.38
    בר
    0.37
     soak
    0.37
    чора
    0.37
     beğ
    0.37
     squir
    0.36
     soaking
    0.36
    Activations Density 0.000%

    No Known Activations