INDEX

Explanations

JavaScript or other C-style code with member access via "." and "->"

oai_token-act-pair · gemini-2.0-flash

._

np_max-act · gemini-2.0-flash

._ Method used: 1 — Because MAX_ACTIVATING_TOKENS are identical ("._") — "._"

np_max-act-logits · gpt-5-mini

Triggered by @chenshw0109

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

-3.78

-2.81

-2.72

-2.64

↵↵

-2.63

<eos>

-2.61

-2.59

-2.58

-2.53

POSITIVE LOGITS

 myſelf

5.34

 Monfieur

5.25

Efq

5.22

 itſelf

5.03

 Majefty

4.91

 purpoſe

4.88

 Jefus

4.84

 ſtate

4.75

 Anſ

4.72

 Reſ

4.72

Activations Density 6.949%

JavaScript or other C-style code with member access via "." and "->"

._

._ Method used: 1 — Because MAX_ACTIVATING_TOKENS are identical ("._") — "._"

No Known Activations

JavaScript or other C-style code with member access via "." and "->"

._

._ Method used: 1 — Because MAX_ACTIVATING_TOKENS are identical ("._") — "._"

No Known Activations