© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 106453
    Prev
    Next
    INDEX
    Explanations

    DynamoDB

    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_44_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
    ەر
    0.42
    αιο
    0.39
     taf
    0.39
     hydration
    0.39
     entreten
    0.38
    ໝ
    0.38
     nền
    0.38
    ceptar
    0.38
     thuyết
    0.37
    ❽
    0.37
    POSITIVE LOGITS
     booked
    0.46
     Booklet
    0.40
     Klasse
    0.39
    }{\
    0.38
     Invasive
    0.38
    精英
    0.38
     Book
    0.37
     Бал
    0.37
    )}{\
    0.37
    奈川
    0.36
    Activations Density 0.002%

    No Known Activations