© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17417
    Prev
    Next
    INDEX
    Explanations

    interest rates monthly

    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_34_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
     hailing
    0.65
     origin
    0.61
     originating
    0.59
    origin
    0.59
    Origin
    0.58
     originate
    0.57
    ancest
    0.56
    祖
    0.55
     ancestral
    0.55
     parents
    0.54
    POSITIVE LOGITS
    淡
    0.40
     Reno
    0.40
    เหมือน
    0.38
     допол
    0.37
     склад
    0.37
    ダメ
    0.36
     заряд
    0.36
     tän
    0.35
     நியூ
    0.35
     vekt
    0.35
    Activations Density 0.012%

    No Known Activations