© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9008
    Prev
    Next
    INDEX
    Explanations

    be aware","consider","use"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ल
    2.55
    ிறது
    2.46
     fatto
    2.24
    netic
    2.22
    ció
    2.21
    𝗟
    2.18
    س
    2.07
     Dienste
    2.00
    𝗥
    1.98
    लया
    1.98
    POSITIVE LOGITS
    я
    2.97
    ة
    2.41
    ed
    2.35
    меча
    2.25
    ್
    2.17
    या
    2.16
    tedir
    2.15
    اة
    2.10
    preferably
    2.04
    ン
    2.03
    Activations Density 0.098%

    No Known Activations