© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203570
    Prev
    Next
    INDEX
    Explanations

    weight

    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_46_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
    bě
    0.42
    ರಿಯ
    0.40
    "-------
    0.39
     Ment
    0.38
     carbono
    0.38
     প্রশাস
    0.38
     Deux
    0.37
    Deux
    0.37
     STRUCTURE
    0.37
     উপকূল
    0.36
    POSITIVE LOGITS
     losing
    0.50
     lose
    0.46
    liert
    0.44
     loses
    0.43
     perder
    0.42
    setPassword
    0.42
    Lose
    0.41
    렀
    0.40
    ارق
    0.40
     Losing
    0.40
    Activations Density 0.002%

    No Known Activations