© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200305
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     T
    0.86
     الت
    0.70
     Т
    0.67
    TP
    0.64
     TPM
    0.61
    Ｔ
    0.61
    𝑇
    0.60
     TP
    0.59
     टी
    0.55
     TPU
    0.55
    POSITIVE LOGITS
    Neil
    0.44
     miếng
    0.42
     Neil
    0.41
     GED
    0.39
    сь
    0.38
    appell
    0.38
     Amos
    0.37
    Q
    0.37
    NIC
    0.37
    foregroundColor
    0.37
    Activations Density 0.033%

    No Known Activations