INDEX

Explanations

=" and : in code

np_max-act-logits · gemini-2.0-flash

specifications of visual elements as used in coding

oai_token-act-pair · gemini-2.0-flash

CSS and HTML properties, dimensions, code snippets

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 EconPapers

-0.84

 насељу

-0.72

 חיצוניים

-0.66

protoimpl

-0.66

مقاله

-0.61

Personendaten

-0.60

 fermés

-0.60

 ouverts

-0.60

 kautta

-0.58

eseorang

-0.57

POSITIVE LOGITS

Xna

0.57

 Italijanski

0.50

 ModelExpression

0.47

0.45

tappe

0.44

 CURLOPT

0.44

Mr

0.43

CURLOPT

0.42

okhttp

0.42

 Frau

0.41

Activations Density 1.496%

=" and : in code

specifications of visual elements as used in coding

CSS and HTML properties, dimensions, code snippets

No Comments

No Known Activations