INDEX

Explanations

code related keywords such as listeners, control elements and conditions

oai_token-act-pair · gemini-2.0-flash

Code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

↵↵

-0.87

↵

-0.72

-0.65

-0.54

Day

-0.52

-0.49

-0.48

↵↵↵

-0.47

POSITIVE LOGITS



1.24

 itſelf

0.90

 Theſe

0.88

tvguidetime

0.86

UnusedPrivate

0.83

 ſch

0.82

 myſelf

0.81

 betweenstory

0.81

 ſche

0.78

ValueStyle

0.75

Activations Density 2.129%

code related keywords such as listeners, control elements and conditions

Code snippets

No Comments

No Known Activations