INDEX

Explanations

a mix of French words and possible grammar errors

oai_token-act-pair · gemini-2.0-flash

multiple languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 BrowserModule

-0.52

pulumi

-0.46

 AssemblyProduct

-0.45

 springfox

-0.41

 forêt

-0.41

Encyklopedia

-0.40

Проце

-0.40

 verwacht

-0.40

 "..\..\

-0.40

AddTagHelper

-0.40

POSITIVE LOGITS

StoryboardSegue

0.91

stretchr

0.68

UnitTesting

0.66

verwijspagina

0.62

 barbati

0.57

 viata

0.57

httphttps

0.57

 băr

0.56

鰭

0.56

GetEnumerator

0.55

Activations Density 0.220%

a mix of French words and possible grammar errors

multiple languages

No Comments

No Known Activations