© 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. 32168
    Prev
    Next
    INDEX
    Explanations

    I can offer

    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
    Ｇ
    0.49
     Reduced
    0.40
     Resin
    0.40
    ｗｗ
    0.39
    ลล์
    0.39
    Ｔ
    0.38
    Ｐ
    0.38
    琨
    0.38
    тельной
    0.38
    dsale
    0.37
    POSITIVE LOGITS
     sacred
    0.43
    ropoda
    0.40
     abc
    0.37
    Space
    0.36
    ظم
    0.35
     patri
    0.35
    raising
    0.35
    }&=
    0.34
     sms
    0.33
    pring
    0.33
    Activations Density 0.006%

    No Known Activations