© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174024
    Prev
    Next
    INDEX
    Explanations

    Perception and wisdom checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    طة
    0.44
    ার্ড
    0.38
     wł
    0.38
    ]".
    0.38
    效
    0.37
     apet
    0.36
    ashore
    0.36
    ጊ
    0.35
     표준
    0.35
    сіі
    0.35
    POSITIVE LOGITS
     overhang
    0.40
    entin
    0.38
    ENSE
    0.34
    INTS
    0.34
    >-
    0.33
     Neuros
    0.33
    णात
    0.33
    *-
    0.32
     not
    0.32
    -(
    0.32
    Activations Density 0.007%

    No Known Activations