© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35205
    Prev
    Next
    INDEX
    Explanations

    hope you enjoy it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     courses
    0.44
     refer
    0.38
    िकेशन
    0.35
    顐
    0.35
     तुम्
    0.35
     weiteren
    0.35
    Optionals
    0.35
    それを
    0.34
     bridges
    0.34
     weiteres
    0.34
    POSITIVE LOGITS
    isot
    0.42
     bukanlah
    0.37
    CHD
    0.37
    慨
    0.36
    oded
    0.36
     deveria
    0.35
    )(=
    0.35
     गृ
    0.34
    šno
    0.34
    Toolset
    0.34
    Activations Density 0.003%

    No Known Activations