© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11771
    Prev
    Next
    INDEX
    Explanations

    phrases that describe something's monetary value

    oai_token-act-pair · gemini-2.0-flash

    say "worth"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     value
    -2.52
     Value
    -2.44
     VALUE
    -2.33
    value
    -2.30
    Value
    -2.20
    VALUE
    -2.08
     Values
    -2.02
     values
    -2.02
     Val
    -1.99
    Val
    -1.98
    POSITIVE LOGITS
    DeleteBehavior
    0.60
    ="@+
    0.59
    SourceChecksum
    0.46
    AnchorTagHelper
    0.46
    AndroidJUnit
    0.45
    OGND
    0.42
    FilterChain
    0.42
    UserScript
    0.41
    তথ্যসূত্র
    0.40
     DPI
    0.40
    Activations Density 1.639%

    No Known Activations