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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1863
    Prev
    Next
    INDEX
    Explanations

    uses forms of the verb "to be" and related words expressing possibility and assessment.

    oai_token-act-pair · gemini-2.0-flash

    positive sentiment

    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
     OK
    -2.48
     ok
    -2.28
    OK
    -2.25
    Ok
    -2.14
     Ok
    -2.00
     okay
    -1.87
    ok
    -1.71
     OKAY
    -1.63
    okay
    -1.55
     Okay
    -1.55
    POSITIVE LOGITS
    ########.
    0.54
     degradability
    0.50
    Personensuche
    0.47
     tendances
    0.47
    ienka
    0.46
     صوتيه
    0.45
    zzleHttp
    0.44
    ynb
    0.44
     Wordle
    0.44
     ricardo
    0.43
    Activations Density 4.977%

    No Known Activations