© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241236
    Prev
    Next
    INDEX
    Explanations

    cultivate unwavering

    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
     novel
    0.35
     disastrous
    0.35
     youngster
    0.33
     }^{
    0.33
    adiene
    0.33
    ungkap
    0.33
     tripled
    0.33
    ayena
    0.33
    தியான
    0.33
    nilai
    0.32
    POSITIVE LOGITS
     Interface
    0.44
     ワイド
    0.41
     svr
    0.40
    infs
    0.38
    า
    0.38
     네
    0.38
    Axes
    0.38
    이트
    0.38
     ит
    0.38
     계
    0.37
    Activations Density 0.000%

    No Known Activations