© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 86971
    Prev
    Next
    INDEX
    Explanations

    not forgotten

    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_23_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
     metais
    0.41
    рии
    0.38
     neuro
    0.38
    ikum
    0.38
    ඩු
    0.38
     breakthrough
    0.37
    󠁥
    0.37
     brick
    0.36
     eloqu
    0.36
    캄
    0.36
    POSITIVE LOGITS
    不错
    0.44
     चूक
    0.42
    เดิน
    0.41
     sobald
    0.40
     सापेक्ष
    0.40
    vdots
    0.39
     הוד
    0.39
    मूलन
    0.39
    ness
    0.39
     συνε
    0.39
    Activations Density 0.041%

    No Known Activations