INDEX

Explanations

text that comes from legal documents, specifically questions or issues

oai_token-act-pair · gemini-2.0-flash

legal questions

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

StoryboardSegue

-0.74

 bezeichneter

-0.74

WebVitals

-0.69

 autorytatywna

-0.65

 للمعارف

-0.64

Numerology

-0.63

MemoryWarning

-0.62

 محفوظة

-0.61

 AssemblyCulture

-0.60

cloudflare

-0.60

POSITIVE LOGITS

 pits

0.65

pit

0.59

concern

0.53

Pit

0.52

 invite

0.52

 concern

0.50

 asks

0.50

pit

0.49

الإنجليزية

0.49

 invites

0.49

Activations Density 7.115%

text that comes from legal documents, specifically questions or issues

legal questions

No Comments

No Known Activations