INDEX

Explanations

code, filenames, and elements within code

oai_token-act-pair · gemini-2.0-flash

technical data

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-1.16

-1.05

-0.98

-0.96

-0.95

-0.93

-0.91

POSITIVE LOGITS

Efq

2.05

 myſelf

2.00

 Theſe

1.96

 Monfieur

1.89

 itſelf

1.85

 pleaſure

1.80

 raiſ

1.79

 ſeveral

1.74

 Jefus

1.73

 Majefty

1.71

Activations Density 1.129%

code, filenames, and elements within code

technical data

No Comments

No Known Activations