© 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. 15925
    Prev
    Next
    INDEX
    Explanations

    the word "rather".

    oai_token-act-pair · gemini-2.0-flash

    rather

    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
    A
    -0.49
    About
    -0.47
     col
    -0.45
    cino
    -0.44
    about
    -0.42
    col
    -0.42
     A
    -0.41
    ABOUT
    -0.41
     
    -0.41
    gya
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    1.01
     kasarigan
    0.82
    SourceChecksum
    0.81
    Portale
    0.80
     متعلقه
    0.75
    ftagPool
    0.73
    RegistryLite
    0.72
     Réponses
    0.72
     onPostExecute
    0.71
    IndentedString
    0.71
    Activations Density 0.990%

    No Known Activations