© 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. 219115
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    كمة
    0.39
    ColorF
    0.38
    Gd
    0.38
     bords
    0.38
    Issue
    0.36
     layouts
    0.36
    策
    0.35
    ওয়্যার
    0.35
     पर्सनल
    0.34
    BorderStyle
    0.34
    POSITIVE LOGITS
     cat
    0.41
     nocturnal
    0.39
    нача
    0.39
     overburden
    0.39
     rammed
    0.38
    惱
    0.38
     stumbling
    0.38
     ram
    0.38
    Literatur
    0.38
     convict
    0.37
    Activations Density 0.016%

    No Known Activations