INDEX

Explanations

the abbreviation "Rep" and related forms

oai_token-act-pair · gemini-2.0-flash

Rep

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

DockStyle

-0.86

addCriterion

-0.74

setVerticalGroup

-0.72

queryInterface

-0.71

IContainer

-0.69

RegressionTest

-0.67

stdc

-0.66

 transférez

-0.65

Atsauces

-0.63

WriteLiteral

-0.62

POSITIVE LOGITS

 Normdatei

0.63

qvarna

0.48

 الاطلاع

0.44

ghton

0.42

iteness

0.42

utusan

0.41

ньше

0.41

 Nationen

0.41

 Parenthood

0.40

ragamo

0.40

Activations Density 2.169%

the abbreviation "Rep" and related forms

Rep

No Comments

No Known Activations