© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10341
    Prev
    Next
    INDEX
    Explanations

    words used to describe taking a course of action

    oai_token-act-pair · gemini-2.0-flash

    say "around"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     around
    -2.73
     Around
    -2.72
    Around
    -2.70
    around
    -2.56
     AROUND
    -2.53
    AROUND
    -2.23
     alrededor
    -2.13
     intorno
    -2.00
     autour
    -1.98
     вокруг
    -1.92
    POSITIVE LOGITS
     AttributeSet
    0.59
     Roskov
    0.54
    DeleteBehavior
    0.52
    Aholisi
    0.52
     eventdata
    0.49
    enten
    0.49
    fjspx
    0.48
    ulsive
    0.48
    mentaux
    0.48
    bergement
    0.48
    Activations Density 3.694%

    No Known Activations