INDEX

Explanations

phrases related to thought, memory and questions

oai_token-act-pair · gemini-2.0-flash

expressing thoughts and feelings

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ſelves

-0.90

ſelf

-0.81

 Majefty

-0.77

 ویکی‌پدیای

-0.75

 itſelf

-0.74

CloseOperation

-0.74

 pleaſure

-0.72

DockStyle

-0.71

 myſelf

-0.71

sizeCache

-0.69

POSITIVE LOGITS

rull

0.47

ẠI

0.46

chapp

0.43

érfi

0.42

pro

0.41

strix

0.41

nosis

0.41

förder

0.41

XmlType

0.40

cea

0.40

Activations Density 0.979%

phrases related to thought, memory and questions

expressing thoughts and feelings

No Comments

No Known Activations