INDEX

Explanations

text found in mathematics or question-answer prompts

oai_token-act-pair · gemini-2.0-flash

unique or specific terms

np_token-act-pair-logits · gpt-4o-mini

Code and documentation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-0.71

-0.70

<em>

-0.65

de

-0.63

</em>

-0.63

</strong>

-0.63

-0.61

...

-0.60

POSITIVE LOGITS

 Theſe

1.26

AndEndTag

1.09

 myſelf

1.01

 Monfieur

1.01

 itſelf

0.99

 bezeichneter

0.97

 faſt

0.93

 pleaſure

0.92

 houſe

0.92

expandindo

0.92

Activations Density 8.031%

text found in mathematics or question-answer prompts

unique or specific terms

Code and documentation

No Comments

No Known Activations