© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157702
    Prev
    Next
    INDEX
    Explanations

    Khajiit, Khichdi, Khufu

    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_2_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
     for
    1.45
    ă
    1.18
    ari
    1.13
     by
    1.10
     malicious
    1.05
    ous
    1.05
     performances
    1.05
     and
    1.03
    ue
    1.02
    :
    1.02
    POSITIVE LOGITS
    ts
    1.41
    اب
    1.30
    f
    1.23
    dır
    1.13
    ského
    1.09
    the
    1.06
    hg
    1.06
    skih
    1.03
    skap
    1.02
    تش
    1.02
    Activations Density 0.000%

    No Known Activations