© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258759
    Prev
    Next
    INDEX
    Explanations

    the love of my life

    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_22_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
    ുകൊണ്ടാണ്
    0.42
    गुन
    0.41
     nervousness
    0.40
     pouze
    0.39
    വോ
    0.39
     untersucht
    0.38
    炲
    0.38
     மகளிர்
    0.38
     madness
    0.38
    ভব
    0.38
    POSITIVE LOGITS
     –
    0.45
     D
    0.43
     Ek
    0.42
     Enlight
    0.42
    erve
    0.42
     Hel
    0.41
     Saga
    0.40
     Spoiler
    0.40
     sette
    0.40
     C
    0.40
    Activations Density 0.001%

    No Known Activations