© 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. 3996
    Prev
    Next
    INDEX
    Explanations

    negative financial trends, especially decreases in sales, revenue, and market share.

    oai_token-act-pair · gemini-2.0-flash

    downward trend

    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
    MLLoader
    -1.11
     صوتيه
    -1.11
     Roskov
    -1.06
     itſelf
    -1.04
    IntoConstraints
    -1.04
    tagHelperRunner
    -1.03
     Jefus
    -1.02
     '\\;'
    -1.02
     otomatig
    -1.01
     المعيارى
    -1.01
    POSITIVE LOGITS
     
    0.80
     by
    0.75
     $
    0.73
     to
    0.65
     just
    0.57
     y
    0.55
     I
    0.54
     ten
    0.54
     from
    0.53
     +
    0.52
    Activations Density 2.040%

    No Known Activations