© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12340
    Prev
    Next
    INDEX
    Explanations

    the word "preference" and words relating to describing the components of a study or experiment

    oai_token-act-pair · gemini-2.0-flash

    preferences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     preferred
    -2.30
     preference
    -2.27
     Preferred
    -2.16
     Prefer
    -2.11
     prefer
    -2.11
     Preference
    -2.08
    prefer
    -2.05
    Preferred
    -2.05
    preferred
    -2.03
    preference
    -2.02
    POSITIVE LOGITS
     P
    0.51
    ViewFeatures
    0.48
    dP
    0.47
    ellites
    0.47
     armée
    0.47
    Dagger
    0.46
    ραγ
    0.46
    P
    0.44
    izers
    0.44
    bzero
    0.44
    Activations Density 2.058%

    No Known Activations