© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 571
    Prev
    Next
    INDEX
    Explanations

    personal pronouns with modal verbs and "to".

    oai_token-act-pair · gemini-2.0-flash

    modal verbs

    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
     Roskov
    -0.52
    Phương
    -0.45
     plead
    -0.41
    CodedInputStream
    -0.39
    KEYCODE
    -0.39
     houver
    -0.38
    ira
    -0.38
     practise
    -0.37
     advise
    -0.37
    routeProvider
    -0.37
    POSITIVE LOGITS
     loose
    1.12
     Loose
    0.99
    loose
    0.98
    Loose
    0.91
     breath
    0.82
     Effect
    0.81
     Setup
    0.78
     Breath
    0.77
     effect
    0.77
    breath
    0.77
    Activations Density 2.779%

    No Known Activations