© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82765
    Prev
    Next
    INDEX
    Explanations

    lone astronaut or figure

    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_0_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
    ↵
    1.39
    做
    1.36
    는
    1.23
    الح
    1.17
    會
    1.15
    อร์
    1.14
    กับ
    1.13
    ش
    1.07
    ৫
    1.01
    ava
    0.97
    POSITIVE LOGITS
    d
    1.82
    lifting
    1.45
    labor
    1.43
    。
    1.41
    l
    1.40
    lh
    1.39
    a
    1.39
    lift
    1.36
    lardan
    1.36
    ri
    1.35
    Activations Density 0.000%

    No Known Activations