© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101019
    Prev
    Next
    INDEX
    Explanations

    peace movement

    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_14_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
    <strong>
    0.46
    Student
    0.46
    User
    0.44
    </tbody>
    0.44
    的生活
    0.44
    ()+
    0.43
     troops
    0.42
    皈
    0.42
    ;&
    0.42
    www
    0.41
    POSITIVE LOGITS
    ंपरिक
    0.57
    𝙮
    0.55
    cyte
    0.52
    泺
    0.51
    𝘺
    0.50
     Laboratories
    0.50
    ிறது
    0.49
     interés
    0.49
     аль
    0.48
    ʸ
    0.48
    Activations Density 0.002%

    No Known Activations