© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59817
    Prev
    Next
    INDEX
    Explanations

    river delta and village

    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_2_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
    í
    0.70
    ia
    0.66
    IA
    0.66
     as
    0.64
    n
    0.63
    ли
    0.61
    ین
    0.61
    ী
    0.61
    ti
    0.59
    री
    0.58
    POSITIVE LOGITS
    "
    0.80
    2
    0.79
    ون
    0.75
    1
    0.74
    (
    0.72
    ни
    0.68
    \
    0.63
    )
    0.61
    하다
    0.59
    ى
    0.59
    Activations Density 0.007%

    No Known Activations