© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6263
    Prev
    Next
    INDEX
    Explanations

    the word "right" plus a preposition or adverb

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "right"

    np_token-act-pair-logits · gpt-4o-mini

    right

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RectangleBorder
    -0.82
    Portale
    -0.78
    nologue
    -0.73
     nahilalakip
    -0.73
    VERY
    -0.68
     very
    -0.68
    دانشنامهٔ
    -0.67
    ValueGenerated
    -0.66
    Quite
    -0.64
    très
    -0.64
    POSITIVE LOGITS
     оригіналу
    0.65
     there
    0.49
     where
    0.44
    addCriterion
    0.43
    ապ
    0.39
    there
    0.39
    CrossRef
    0.39
    sphinx
    0.38
     économiques
    0.38
     "..\..\
    0.37
    Activations Density 0.228%

    No Known Activations