© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33024
    Prev
    Next
    INDEX
    Explanations

    brand 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
    Syntax
    0.39
    ኔ
    0.39
    莉
    0.39
     Nickel
    0.38
    BY
    0.38
    𝕂
    0.38
     نع
    0.36
    Attach
    0.36
     Kee
    0.35
     بث
    0.35
    POSITIVE LOGITS
     A
    0.50
    mike
    0.47
     porridge
    0.43
     _$_
    0.42
     Rxe
    0.40
    cere
    0.39
    亼
    0.38
    礬
    0.38
     Gebiet
    0.38
    miri
    0.38
    Activations Density 0.000%

    No Known Activations