INDEX

Explanations

html table elements

oai_token-act-pair · gemini-2.0-flash

</td>

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

cshtml

-0.62

-0.52

-0.46

-0.45

zu

-0.44

 John

-0.43

stück

-0.42

tu

-0.42

POSITIVE LOGITS

 Audiodateien

0.89

 poffible

0.80

IUrlHelper

0.79

 Majefty

0.78

 فريبيس

0.78

 fubject

0.77

 Monfieur

0.73

Aktualisiert

0.72

 myſelf

0.72

 perfons

0.71

Activations Density 0.863%

html table elements

&lt;/td&gt;

No Comments

No Known Activations

</td>