INDEX

Explanations

code snippets, music recording information, and cancer treatment terminology

oai_token-act-pair · gemini-2.0-flash

single letters

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Majefty

-0.81

 Monfieur

-0.80

 itſelf

-0.79

 myſelf

-0.73

ſelves

-0.73

Efq

-0.71

 purpoſe

-0.69

 Theſe

-0.69

 Jefus

-0.68

 Anſ

-0.68

POSITIVE LOGITS

0.61

MA

0.60

0.58

0.57

0.55

cs

0.54

CH

0.54

com

0.54

Activations Density 3.918%

code snippets, music recording information, and cancer treatment terminology

single letters

No Comments

No Known Activations