© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35441
    Prev
    Next
    INDEX
    Explanations

    impossible tasks

    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_31_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
    업
    0.45
     circonst
    0.44
    㮆
    0.40
     वरि
    0.38
     episodios
    0.38
    IPS
    0.38
     വ്യാ
    0.38
    鹑
    0.38
     Grandes
    0.36
    contr
    0.36
    POSITIVE LOGITS
    쌈
    0.42
     bub
    0.38
    bub
    0.37
    <unused56>
    0.35
    gebäude
    0.35
     trachea
    0.35
    ('=
    0.35
     vliegtuig
    0.34
     race
    0.34
     staked
    0.34
    Activations Density 0.006%

    No Known Activations