© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213720
    Prev
    Next
    INDEX
    Explanations

    social networks

    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_43_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
     Frog
    0.45
     FRO
    0.41
    েশ্বর
    0.40
     ladd
    0.38
    鲨
    0.38
     définitive
    0.37
     장애
    0.37
    俪
    0.36
     Waller
    0.36
     മാന
    0.36
    POSITIVE LOGITS
    𒁍
    0.42
     INITIAL
    0.38
    poems
    0.38
    நில
    0.37
     образовањем
    0.37
     користу
    0.37
    DIST
    0.36
    Priv
    0.36
    dist
    0.36
    urna
    0.36
    Activations Density 0.001%

    No Known Activations