© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46848
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    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
    gypt
    0.84
     uczni
    0.83
    هم
    0.80
    ت
    0.78
     उम्मीदवार
    0.78
    抂
    0.75
    哳
    0.75
    טת
    0.73
    ్రీన్
    0.73
    wl
    0.71
    POSITIVE LOGITS
    .
    0.83
     helplessly
    0.76
    ↵
    0.75
     beaming
    0.74
     বেশির
    0.70
    ﻢ
    0.70
     brake
    0.70
     heterocyclic
    0.69
     financially
    0.69
     має
    0.66
    Activations Density 0.027%

    No Known Activations