© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5346
    Prev
    Next
    INDEX
    Explanations

    expressions of strong (often negative) emotions, often as part of larger pronouncements of opinion

    oai_token-act-pair · gemini-2.0-flash

    personal opinions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -1.64
     myſelf
    -1.59
     itſelf
    -1.55
     виправивши
    -1.52
    LookAnd
    -1.52
     Efq
    -1.45
     Monfieur
    -1.44
     raiſ
    -1.42
     <=",
    -1.41
    EDEFAULT
    -1.40
    POSITIVE LOGITS
    se
    0.54
    r
    0.54
    t
    0.54
    n
    0.53
      
    0.53
    v
    0.53
     (
    0.52
    ts
    0.52
    ini
    0.51
    ↵
    0.51
    Activations Density 69.358%

    No Known Activations