© 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. 1094
    Prev
    Next
    INDEX
    Explanations

    words related to driving, specifically mentioning features or modes in cars

    oai_token-act-pair · gemini-2.0-flash

    Car handling and performance

    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
    HtmlAttribute
    -0.75
     <<<<<<<<<<<<<<
    -0.71
     дописавши
    -0.63
     مشين
    -0.62
    DebuggerNonUser
    -0.60
    ]")]
    -0.58
    :]:
    -0.58
     ]
    -0.57
    rrggbb
    -0.56
     ]];
    -0.53
    POSITIVE LOGITS
    İstinadlar
    0.67
    
    0.56
     BoxFit
    0.52
    GeneratedCode
    0.50
     vouloir
    0.50
    municipi
    0.46
     Humphrey
    0.45
    Tracce
    0.44
     متعلقه
    0.44
    onge
    0.44
    Activations Density 3.166%

    No Known Activations