INDEX

Explanations

HTML image tags and possibly also surrounding structural tags for web pages

oai_token-act-pair · gemini-2.0-flash

img

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 InputDecoration

-0.40

Standard

-0.38

 standard

-0.38

 Standard

-0.37

록

-0.37

apha

-0.36

метров

-0.35

mappedBy

-0.34

serde

-0.34

 Loew

-0.34

POSITIVE LOGITS

UserScript

0.77

}';

0.73

AccessorTable

0.73

 мәкал

0.71

ruptedException

0.70

iconque

0.69

tableFuture

0.68

InjectAttribute

0.68

 ostavi

0.67

]').

0.66

Activations Density 2.011%

HTML image tags and possibly also surrounding structural tags for web pages

img

No Comments

No Known Activations