© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15307
    Prev
    Next
    INDEX
    Explanations

    German sentences, especially those discussing hypothetical situations

    oai_token-act-pair · gemini-2.0-flash

    say "ver words"

    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
    Negative Logits
    AxisAlignment
    -0.80
     EconPapers
    -0.72
     kasarigan
    -0.71
     ModelExpression
    -0.70
    bootstrapcdn
    -0.69
    Personendaten
    -0.67
     raiſ
    -0.66
    AndEndTag
    -0.65
     متعلقه
    -0.65
     themſelves
    -0.65
    POSITIVE LOGITS
     ver
    0.56
    ver
    0.56
    Ver
    0.51
     Ver
    0.47
     VER
    0.43
    IsMutable
    0.41
    VER
    0.40
    vered
    0.37
    eren
    0.36
     verd
    0.36
    Activations Density 0.161%

    No Known Activations