INDEX

Explanations

large numbers, especially those including exponents, percentages, or those that specify ratios or measurements

oai_token-act-pair · gemini-2.0-flash

potentially archaic texts

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

-1.20

-1.16

-1.14

↵

-1.13

<eos>

-1.08

↵↵

-1.08

-1.07

-1.06

POSITIVE LOGITS

Efq

2.13

 Theſe

2.03

 myſelf

1.98

 Monfieur

1.88

 itſelf

1.85

 Jefus

1.77

ſelf

1.76

 purpoſe

1.74

 pleaſure

1.74

 Anſ

1.73

Activations Density 2.212%

large numbers, especially those including exponents, percentages, or those that specify ratios or measurements

potentially archaic texts

No Comments

No Known Activations