© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205868
    Prev
    Next
    INDEX
    Explanations

    "kith and kin" or "Three Bodies" or "padre rico"

    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_25_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
     pł
    0.25
     poderes
    0.25
     rhin
    0.25
    砓
    0.24
     oś
    0.24
     شر
    0.24
     pollut
    0.24
     hlav
    0.24
     probate
    0.24
     ومل
    0.24
    POSITIVE LOGITS
    eto
    0.29
    \|+\
    0.28
    人が
    0.28
    কন
    0.28
     санти
    0.28
     మనం
    0.26
    spirator
    0.26
    eyiz
    0.25
    तमंद
    0.25
    ངས་
    0.25
    Activations Density 0.000%

    No Known Activations