© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7226
    Prev
    Next
    INDEX
    Explanations

    German text discussing verbs, especially modal verbs and how they can be combined.

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     he
    -0.49
     He
    -0.45
     (
    -0.44
    ULTY
    -0.41
     Ver
    -0.41
     C
    -0.41
     
    -0.41
     she
    -0.41
     be
    -0.40
     post
    -0.40
    POSITIVE LOGITS
     CURIAM
    0.82
    Personendaten
    0.77
    verwijspagina
    0.72
     Eben
    0.70
    interopRequire
    0.70
     greateſt
    0.68
     SwitchCompat
    0.68
    ).]
    0.66
     themſelves
    0.65
     Theſe
    0.65
    Activations Density 0.468%

    No Known Activations