© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36274
    Prev
    Next
    INDEX
    Explanations

    consideration and politeness

    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_11_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
    h
    0.85
    f
    0.76
    b
    0.67
    j
    0.67
    z
    0.66
    er
    0.66
    som
    0.66
    r
    0.65
    et
    0.64
    y
    0.64
    POSITIVE LOGITS
     khẩu
    0.67
     ಅನ್ನು
    0.62
    ภัณฑ์
    0.59
     Buckeyes
    0.59
     regioni
    0.59
     scena
    0.58
     corpi
    0.57
    ificazione
    0.57
     matcha
    0.57
     strada
    0.56
    Activations Density 0.000%

    No Known Activations