© 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. 6617
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing possibility or describing abstract situations involving change or transition

    oai_token-act-pair · gemini-2.0-flash

    play

    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
    umoj
    -0.46
     Regency
    -0.45
    esModule
    -0.45
     nakalista
    -0.45
    WEBPACK
    -0.44
    Cyfarwyddwr
    -0.41
    ABAD
    -0.41
     Emig
    -0.40
     soud
    -0.40
     Wirt
    -0.40
    POSITIVE LOGITS
     play
    2.84
     playing
    2.59
     plays
    2.56
     played
    2.48
    play
    2.47
     Play
    2.34
    Play
    2.34
     Playing
    2.33
    plays
    2.30
     Plays
    2.25
    Activations Density 5.889%

    No Known Activations