INDEX

Explanations

the word "pass" in varous contexts.

oai_token-act-pair · gemini-2.0-flash

pass

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 passing

-3.09

 passed

-3.06

 passes

-3.03

 Passing

-2.94

 pass

-2.92

 Pass

-2.89

 Passes

-2.83

Passing

-2.81

 PASS

-2.80

Pass

-2.78

POSITIVE LOGITS

Renderer

0.40

 torne

0.38

 Daher

0.37

چال

0.36

はじめに

0.36

cha

0.35

og

0.35

쓰

0.34

ga

0.34

cho

0.34

Activations Density 0.796%

the word "pass" in varous contexts.

pass

No Comments

No Known Activations