© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214534
    Prev
    Next
    INDEX
    Explanations

    official & technical contexts

    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_47_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
    пах
    0.40
    化物
    0.40
    𝗸
    0.40
    務
    0.39
    兘
    0.38
    닝
    0.38
     Maurizio
    0.38
    铯
    0.38
     Farmer
    0.37
     Jesse
    0.37
    POSITIVE LOGITS
    é
    0.43
    endu
    0.41
    FORWARD
    0.36
     वि
    0.36
    सु
    0.36
     فت
    0.36
    amment
    0.35
    Places
    0.35
    DEVELOP
    0.35
    rale
    0.35
    Activations Density 0.000%

    No Known Activations