© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11272
    Prev
    Next
    INDEX
    Explanations

    temperatures reported in degrees Celsius

    oai_token-act-pair · gemini-2.0-flash

    Degree symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    °
    -2.22
    °.
    -1.55
    °,
    -1.46
     °
    -1.42
    º
    -1.27
    °-
    -1.23
    °)
    -1.12
    °;
    -1.11
    °/
    -1.08
    ˚
    -1.02
    POSITIVE LOGITS
    GoogleApiClient
    0.56
    ]=-
    0.51
    Portály
    0.51
    dAtA
    0.51
    cetta
    0.51
     onlyOwner
    0.50
    \}=
    0.50
    OLDS
    0.49
    elernt
    0.49
    bandcamp
    0.49
    Activations Density 1.309%

    No Known Activations