© 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
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109991
    Prev
    Next
    INDEX
    Explanations

    bot:

    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
    tedir
    1.19
    v
    1.16
    id
    1.16
    SC
    1.10
    SO
    1.09
    CE
    1.08
    دی
    1.08
    DC
    1.06
    ⺀
    1.05
     postaci
    1.04
    POSITIVE LOGITS
    <0x0D>
    1.39
    ி
    1.12
    li
    1.08
     Its
    1.06
    </td>
    1.05
    ter
    1.02
    </h3>
    1.00
     VMs
    0.98
    ৯
    0.97
     لأ
    0.96
    Activations Density 0.000%

    No Known Activations