INDEX

Explanations

words related to mechanics.

oai_token-act-pair · gemini-2.0-flash

lines, borders, positions, spaces

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

 sebut

-0.46

amerika

-0.45

 geene

-0.42

顿

-0.38

ußen

-0.38

 bruto

-0.38

tanooga

-0.38

agner

-0.37

 elef

-0.37

ém

-0.37

POSITIVE LOGITS

 مشين

0.89

EndInit

0.87

AndEndTag

0.83

Personendaten

0.79

HtmlAttribute

0.77

///</

0.76

DebuggerNonUser

0.75

DockStyle

0.74

InstanceState

0.72

XmlAccessType

0.71

Activations Density 38.588%

words related to mechanics.

lines, borders, positions, spaces

No Comments

No Known Activations