© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142998
    Prev
    Next
    INDEX
    Explanations

    alternating, alternatives, alternation

    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
    л
    1.48
    ре
    1.46
    la
    1.44
    ۳
    1.25
    \
    1.24
    す
    1.22
    ä
    1.21
    ce
    1.18
    lan
    1.18
    mi
    1.16
    POSITIVE LOGITS
    ي
    1.73
    та
    1.54
    0
    1.31
    <0x80>
    1.29
     پیسې
    1.27
    on
    1.25
     reeks
    1.22
    س
    1.20
    ี
    1.19
     raffin
    1.18
    Activations Density 0.000%

    No Known Activations