INDEX

Explanations

words related to the human body, disease, anatomy, and medical treatments.

oai_token-act-pair · gemini-2.0-flash

structure

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

uxxxx

-1.03

EDEFAULT

-1.02

 Мексичка

-1.01

BufferException

-0.99

IsMutable

-0.96

WriteTagHelper

-0.96

IntoConstraints

-0.95

 AssemblyCulture

-0.94

Tikang

-0.94

 Taktlose

-0.89

POSITIVE LOGITS

 structure

1.67

 Structure

1.45

structure

1.45

 structures

1.44

 body

1.27

Structure

1.22

 Structures

1.19

 STRUCTURE

1.18

structures

1.13

结构

1.09

Activations Density 3.816%

words related to the human body, disease, anatomy, and medical treatments.

structure

No Comments

No Known Activations