© 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. 198928
    Prev
    Next
    INDEX
    Explanations

    problem or change

    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
     दुष्प्रभावों
    0.41
    Determ
    0.40
     determinados
    0.40
     determinado
    0.39
     incomplète
    0.39
     MICRO
    0.38
    BlogPost
    0.38
    ཌ
    0.38
     determinada
    0.37
    determ
    0.36
    POSITIVE LOGITS
    Problem
    0.46
     Problem
    0.44
     Change
    0.42
     문제
    0.41
     haven
    0.41
     problem
    0.40
    Change
    0.40
     Mud
    0.40
    更改
    0.40
     Moment
    0.38
    Activations Density 0.000%

    No Known Activations