© 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. 161378
    Prev
    Next
    INDEX
    Explanations

    villainous

    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
    ח
    1.36
    ্ব
    1.15
    리
    1.12
    ק
    1.11
    ু
    1.09
    ك
    1.05
    ัน
    1.03
    ун
    1.02
     publica
    1.02
    ע
    0.99
    POSITIVE LOGITS
    d
    1.41
    t
    1.29
    name
    1.26
    less
    1.25
    land
    1.22
    ly
    1.16
    ring
    1.15
    ting
    1.13
    scopic
    1.13
    个
    1.10
    Activations Density 0.000%

    No Known Activations