© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176815
    Prev
    Next
    INDEX
    Explanations

    absorb

    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
     S
    0.55
     الس
    0.46
    oj
    0.43
    S
    0.42
     ச
    0.42
     DOA
    0.40
    𝑆
    0.39
     ಸ
    0.39
    SA
    0.39
    ச
    0.38
    POSITIVE LOGITS
    ലാണ്
    0.40
    aliy
    0.37
    Kris
    0.37
    omiast
    0.36
     aldığı
    0.36
    anchen
    0.36
    ハマ
    0.36
    wick
    0.35
     implicated
    0.35
    吴
    0.35
    Activations Density 0.002%

    No Known Activations