© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219724
    Prev
    Next
    INDEX
    Explanations

    random number generation

    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_31_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
     이름을
    0.43
     名称
    0.42
    ተት
    0.37
    甕
    0.37
    名称
    0.36
     именем
    0.36
    疼
    0.35
    setName
    0.35
    名前
    0.35
    清楚
    0.35
    POSITIVE LOGITS
    Preliminary
    0.42
    堬
    0.42
     preliminary
    0.40
     Preliminary
    0.38
     ciné
    0.37
    說
    0.37
     endian
    0.35
     Bonn
    0.35
    Clip
    0.35
    defini
    0.35
    Activations Density 0.001%

    No Known Activations