INDEX

Explanations

mentions of trails, paths and routes

oai_token-act-pair · gemini-2.0-flash

path or trail

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 يتيمه

-0.83

IndentedString

-0.81

MessageOf

-0.75

 Италијани

-0.74

IUrlHelper

-0.74

+#+#

-0.71

 autorytatywna

-0.67

 Мексичка

-0.66

RTEE

-0.66

 HasFactory

-0.66

POSITIVE LOGITS

 track

0.79

 path

0.71

 thread

0.68

 pathway

0.64

 tracks

0.64

 pathways

0.61

 trail

0.60

 trace

0.60

 paths

0.59

 PATH

0.59

Activations Density 1.393%

mentions of trails, paths and routes

path or trail

No Comments

No Known Activations