© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41978
    Prev
    Next
    INDEX
    Explanations

    as little as, as young as, as low as

    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_22_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
     Klasse
    0.44
    例
    0.42
     vac
    0.39
     verschill
    0.37
     चा
    0.36
    บาง
    0.35
     రామ
    0.35
    种种
    0.35
    テック
    0.35
     먹
    0.35
    POSITIVE LOGITS
    Ø
    0.46
    នា
    0.43
    xs
    0.42
    𝘞
    0.42
     Montserrat
    0.41
    mana
    0.40
    アリング
    0.40
     generando
    0.40
    보다는
    0.40
    ustain
    0.40
    Activations Density 0.001%

    No Known Activations