© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7364
    Prev
    Next
    INDEX
    Explanations

    descriptions of the flavor and aroma of olive oil

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    extAlignment
    -0.59
    UnknownFieldSet
    -0.59
     ():
    -0.55
     burn
    -0.54
     comuniques
    -0.52
    }{%
    -0.51
    AndroidJUnit
    -0.51
     CreateTagHelper
    -0.51
    Istorija
    -0.50
     **)
    -0.50
    POSITIVE LOGITS
    queryInterface
    0.57
    AnchorTagHelper
    0.55
     NavController
    0.54
    帖最后由
    0.51
     nakalista
    0.51
     صوتيه
    0.50
    __':
    0.50
    ynchrotron
    0.50
    InitVars
    0.49
     bross
    0.47
    Activations Density 1.168%

    No Known Activations