© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12803
    Prev
    Next
    INDEX
    Explanations

    sentences in German using modal verbs such as können, gehen, hören, and hätte.

    oai_token-act-pair · gemini-2.0-flash

    non-English context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.98
    also
    -1.50
    Also
    -1.45
     Also
    -1.39
     ALSO
    -1.13
     también
    -1.11
     também
    -1.07
     также
    -0.94
     juga
    -0.90
     également
    -0.88
    POSITIVE LOGITS
    帖最后由
    0.82
    extAlignment
    0.74
     surla
    0.71
    rungsseite
    0.70
     виправивши
    0.70
    CompleteListener
    0.70
     متحده
    0.68
    Lycka
    0.68
     CreateTagHelper
    0.67
     intStringLen
    0.67
    Activations Density 0.472%

    No Known Activations