© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33699
    Prev
    Next
    INDEX
    Explanations

    often followed by actions or states

    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_7_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
    ts
    0.62
    us
    0.58
    y
    0.57
    ns
    0.55
    i
    0.55
    z
    0.54
    os
    0.52
    ss
    0.52
    ta
    0.52
    dell
    0.50
    POSITIVE LOGITS
     toilets
    0.44
     silo
    0.42
     física
    0.42
     overclock
    0.41
     políticas
    0.40
     độ
    0.40
     акчага
    0.40
     orifices
    0.39
     regole
    0.39
     питание
    0.38
    Activations Density 0.040%

    No Known Activations