© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80969
    Prev
    Next
    INDEX
    Explanations

    sounds or vowel sounds

    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_53_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
     ¿
    0.43
     Ellen
    0.40
     Flücht
    0.39
    ¿
    0.37
    㸳
    0.36
    玝
    0.36
    ἶ
    0.34
     stainless
    0.34
    妿
    0.34
     stabilité
    0.34
    POSITIVE LOGITS
     paa
    0.53
    AAE
    0.51
    oe
    0.48
    POE
    0.47
     Kue
    0.46
    Foe
    0.46
    baa
    0.46
     saa
    0.45
    Oe
    0.45
    faa
    0.45
    Activations Density 0.005%

    No Known Activations