INDEX

Explanations

code snippets or programming-related text, especially those containing dollar signs, parentheses, and file references.

oai_token-act-pair · gemini-2.0-flash

this

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

DON

-0.38

켰

-0.38

beforeAll

-0.38

潔

-0.38

끼

-0.37

طلحات

-0.37

qual

-0.37

انه

-0.37

subplots

-0.36

 entr

-0.35

POSITIVE LOGITS

 this

2.63

this

2.47

This

1.90

 THIS

1.75

THIS

1.73

 This

1.72

 này

1.58

 questo

1.46

 questa

1.39

 cette

1.37

Activations Density 1.917%

code snippets or programming-related text, especially those containing dollar signs, parentheses, and file references.

this

No Known Activations

code snippets or programming-related text, especially those containing dollar signs, parentheses, and file references.

this

No Known Activations