© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122036
    Prev
    Next
    INDEX
    Explanations

    contact number

    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_3_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
     Contact
    0.89
    CONTACT
    0.88
     kontakt
    0.84
    Contact
    0.82
    contact
    0.82
     kontak
    0.82
    ي
    0.81
    Kontakt
    0.79
     Kontakt
    0.78
     contactos
    0.78
    POSITIVE LOGITS
    ksi
    0.64
     regionally
    0.59
    ,
    0.59
    ]
    0.58
     nationally
    0.57
    jasama
    0.55
     wildly
    0.54
    kannya
    0.54
    N
    0.54
     rekind
    0.53
    Activations Density 0.005%

    No Known Activations