© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119924
    Prev
    Next
    INDEX
    Explanations

    moving closer

    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_27_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
     पाण्याची
    0.41
    <unused74>
    0.40
    Zach
    0.38
    ylsulfanyl
    0.37
    rafpunkte
    0.36
     заду
    0.36
    GetResponse
    0.35
    Khokhlov
    0.35
    Cho
    0.35
     renversement
    0.34
    POSITIVE LOGITS
    ا
    0.40
     particularly
    0.38
     President
    0.35
     closer
    0.34
    ,"
    0.34
     place
    0.33
     etc
    0.33
     backgrounds
    0.33
     Wob
    0.32
     mainstream
    0.32
    Activations Density 0.003%

    No Known Activations