© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108301
    Prev
    Next
    INDEX
    Explanations

    kingdom following prepositions

    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
    ن
    1.72
    ע
    1.65
    ك
    1.61
    ج
    1.32
    ش
    1.31
    ين
    1.28
    ある
    1.23
    ને
    1.20
    اً
    1.20
    ان
    1.18
    POSITIVE LOGITS
    0
    1.39
    ０
    1.11
    ᱐
    0.96
    I
    0.92
    𝟎
    0.85
    is
    0.82
    𝟬
    0.80
    ኼ
    0.80
    ının
    0.79
    ๐
    0.79
    Activations Density 0.001%

    No Known Activations