© 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. 199999
    Prev
    Next
    INDEX
    Explanations

    say "f" words

    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
    ionado
    0.39
     متحد
    0.39
    ="%
    0.38
    utung
    0.36
    ုတ်
    0.36
    ":{"
    0.35
    атра
    0.35
    })-(\
    0.35
     হিন্দি
    0.35
    "%
    0.34
    POSITIVE LOGITS
     Follow
    2.70
     follow
    2.67
    Follow
    2.59
    follow
    2.47
     FOLLOW
    2.34
     follows
    2.19
     followup
    2.14
    FOLLOW
    2.05
    follows
    2.03
     followed
    1.96
    Activations Density 0.001%

    No Known Activations