© 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. 31421
    Prev
    Next
    INDEX
    Explanations

    liberation

    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
     मौ
    0.39
     cloths
    0.39
    Pub
    0.38
    Cloth
    0.35
     cloth
    0.34
     HUB
    0.34
     Cloth
    0.34
     δ
    0.34
     délic
    0.34
    구나
    0.34
    POSITIVE LOGITS
    解放
    1.47
     liberation
    1.39
     освобо
    1.38
     зві
    1.34
     Liberation
    1.26
     liberación
    1.20
    释放
    1.13
     liberated
    1.11
     liberating
    1.09
     liberate
    1.07
    Activations Density 0.001%

    No Known Activations