© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197643
    Prev
    Next
    INDEX
    Explanations

    apple falling, IDX integration

    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_15_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
    an
    0.61
     so
    0.51
     INST
    0.51
    Inst
    0.51
     neben
    0.50
     doomed
    0.48
     Moyen
    0.48
    ᆷ
    0.48
    umbs
    0.48
    আপনি
    0.47
    POSITIVE LOGITS
     Controversy
    0.49
    klore
    0.47
     colori
    0.46
    读书
    0.46
    律师
    0.46
     päät
    0.46
     banane
    0.44
    商城
    0.44
    사진
    0.44
    槐
    0.43
    Activations Density 0.000%

    No Known Activations