© 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. 132964
    Prev
    Next
    INDEX
    Explanations

    technical details

    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
     satan
    0.42
     SSB
    0.41
     Howard
    0.40
     Pard
    0.40
     sammeln
    0.39
     وین
    0.38
     Ravi
    0.38
     හ
    0.38
     সম্মিল
    0.38
     serveur
    0.38
    POSITIVE LOGITS
    षे
    0.40
    CTT
    0.39
    षि
    0.38
    °-
    0.38
    ólico
    0.37
    能源
    0.37
    ꒦
    0.37
     panels
    0.35
    <0x8B>
    0.35
    }-${
    0.35
    Activations Density 0.000%

    No Known Activations