© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36998
    Prev
    Next
    INDEX
    Explanations

    vanilla and related sounds

    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_3_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
    t
    0.96
    1
    0.96
    '
    0.88
    sd
    0.77
    :
    0.76
    tion
    0.75
    /
    0.74
    ya
    0.74
    ه
    0.70
    tg
    0.70
    POSITIVE LOGITS
    ના
    0.73
    ți
    0.72
    즈
    0.69
    в
    0.68
    ンの
    0.65
     сам
    0.64
     busier
    0.64
     quadro
    0.64
     souci
    0.64
    னு
    0.63
    Activations Density 0.000%

    No Known Activations