© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88133
    Prev
    Next
    INDEX
    Explanations

    environmentally

    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_60_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
     അവര്‍
    0.44
     इसकी
    0.43
    这就
    0.43
     इससे
    0.43
    Spectrum
    0.43
     இவை
    0.42
    Drug
    0.41
    牒
    0.41
     इनसे
    0.40
    Straw
    0.39
    POSITIVE LOGITS
     sound
    1.40
     sounded
    1.06
     Sound
    1.02
    sound
    1.00
    Sound
    0.96
     SOUND
    0.93
    サウンド
    0.90
     sounds
    0.90
     зву
    0.88
     sonido
    0.88
    Activations Density 0.002%

    No Known Activations