© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35593
    Prev
    Next
    INDEX
    Explanations

    give birth

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ujacy
    0.39
    ukat
    0.38
     っ
    0.38
    इए
    0.37
    狗
    0.35
    zzo
    0.35
    inės
    0.35
    ovati
    0.35
    sy
    0.35
    nię
    0.35
    POSITIVE LOGITS
    ริง
    0.42
    Gradle
    0.40
     Emerson
    0.38
     Hauser
    0.38
    ᴿ
    0.38
    ስማ
    0.38
    ფერ
    0.37
     Chester
    0.37
    積極的に
    0.37
     ferm
    0.36
    Activations Density 0.000%

    No Known Activations