© 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. 30802
    Prev
    Next
    INDEX
    Explanations

    retain, own, control, forever

    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
     doctrina
    0.41
    鞅
    0.39
    doctrine
    0.39
    nard
    0.37
    ناصر
    0.36
     zn
    0.36
    Mir
    0.36
     rehabilitation
    0.35
    нче
    0.35
    蘼
    0.35
    POSITIVE LOGITS
     Keep
    0.41
     retain
    0.41
     KEEP
    0.39
     retained
    0.39
     Retention
    0.37
    確
    0.37
     keep
    0.37
    㳒
    0.36
     Déf
    0.36
    囲
    0.36
    Activations Density 0.033%

    No Known Activations