© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 159469
    Prev
    Next
    INDEX
    Explanations

    diatomaceous earth

    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
    c
    1.63
    man
    1.30
    ية
    1.20
    om
    1.13
    ма
    1.09
    .
    1.09
    𝐜
    1.05
    the
    1.04
     igen
    1.04
     It
    1.02
    POSITIVE LOGITS
    ה
    2.08
    З
    1.39
    ために
    1.38
    া
    1.27
    트
    1.27
    Ｓ
    1.26
    지
    1.21
    П
    1.20
    𝗦
    1.18
    ه
    1.17
    Activations Density 0.000%

    No Known Activations